Full-Stack Engineer (AI-Native) — AgentX

🏢 Summary: Mid-level React/TypeScript Engineer role focused on building and owning production-grade frontend applications (dashboards, operator panels, customer apps) on top of AI agent systems. The position involves close collaboration with backend services and active use of AI coding tools while maintaining strong engineering judgment and code quality. You will take full ownership of features from design to deployment in a production environment with real users. 🗂️ Requirements: 3–5 years commercial experience in frontend development, Strong proficiency in TypeScript, Deep understanding of React and rendering lifecycle, Experience building scalable frontend architectures, Experience integrating with REST APIs and authentication systems, Ability to work with backend technologies (Node.js or Python), Experience with state management and data synchronization, Proficiency with Next.js, Experience working with MongoDB, Experience deploying or working with AWS, Ability to use AI coding tools critically and effectively 📃 Skills: TypeScript, React, Next.js, Tailwind, Node.js, Python, MongoDB, AWS, REST, Claude, Cursor, MCP 🏢 Description: Who we are AgentX is a platform for building and running production AI agents - and a team that ships real systems on top of it for clients who need more than a demo. The platform is the infrastructure: orchestration, memory, tools, evals, deployment - the layer that makes agentic systems actually work in production. On top of it, we build end-to-end solutions for our clients. One of the systems running on AgentX today is KsięgoBoty - a multi-agent product used daily by hundreds of Polish accounting firms. Paying customers, production load, real consequences when something breaks. We're small, technical, AI-heavy, and we ship. Who we're looking for A solid React engineer who actually understands what's happening under the hood, and uses AI tools daily without outsourcing their brain to them. You'll join the team that owns the user-facing layer of our products: the dashboards, the operator panels, the customer-facing apps that sit on top of the agents. We need someone we can trust to take a feature, build it well, and ship it without it coming back broken three days later. This isn't a flashy role and we're not looking for a flashy person. We need craftsmanship. If you read a ticket and your first instinct is "what's the data model, what's the component structure, where does state actually live" - keep reading. If your first instinct is "I'll just vibe-code it with Cursor and hope the PR passes" - this isn't for you, and that's fine. What we mean by "good React engineer" You write TypeScript well: types help you, they don't slow you down You understand React deeply enough to debug a re-render problem without guessing You can structure a non-trivial frontend so it doesn't turn into a tangle in six months You've worked with a real backend: REST, auth, data sync, edge cases — and you can hold both ends of a feature in your head You read other people's code carefully and review like an adult: kindly, but honestly You are comfortable using AI tools daily, but you do not outsource your judgment to them You know how to check AI-generated code instead of trusting it because it “looks right” ~3–5 years of commercial experience is roughly where we expect this person to sit. Less is fine if you're sharp; more is fine if you actually want a Mid role. How we work with AI We use AI heavily. Claude Code, Codex, Cursor, MCP, agent workflows: they're a normal part of how we work, the same way Git or Docker is. You'll be expected to use them the same way: not as a gimmick, not as a shortcut around understanding the codebase, but as leverage. That means: break work into clear chunks, guide the tools through implementation, review their output critically, fix what's wrong, and own the final result. You should be faster with these tools than without them - and you should know exactly where they're about to lie to you. AI doesn't turn a bad engineer into a good one. It just makes them ship faster, which is worse. So: We do not want people who only know how to prompt. We also do not want people who proudly refuse to use AI and treat it like autocomplete with better marketing. The right person sits in the middle: strong fundamentals, strong taste, strong ownership - multiplied by modern AI tooling. What you'll actually own Frontend, day-to-day. React, TypeScript, Tailwind, Next.js. Real product surfaces - operator dashboards, customer panels, internal tools that real people use to do real work. Fullstack when needed. You won't live exclusively in the frontend. Node/Python on the backend when a feature needs it - you don't have to be an expert, but you have to be willing. Quality. The thing you ship works, doesn't break the next thing, and doesn't make the codebase worse. We notice this. Working with the team. Code reviews, architecture decisions - we figure out the harder calls together. You're not coding in a vacuum. The stack TypeScript / React / Next.js · Tailwind · Node.js · Python (some) · MongoDB · AWS · Claude / Cursor / MCP for tooling. We don't use Go. Nice-to-have (not required) You've built a side project that you actually shipped, not just started You've worked with LLM APIs in production (not "I made a chatbot in a tutorial") You care about UX - not as a designer, but as someone who notices when something feels wrong What we offer 13 000 – 18 000 PLN netto + VAT, B2B Remote-friendly, Poland-based A small team that ships and doesn't waste your time Direct work with the founders - no Jira theater, no three-round groomings, no PM filtering your ideas Modern AI tooling fully paid for (Claude Max, Cursor, Codex, whatever helps you work better) Real ownership of the frontend layer of a product people use every day How the process works 1. You send us stuff recruitment@agentx.so Your CV — yes, we read them One thing you built end-to-end you're proud of — and what you'd change about it today One AI product (yours or someone else's) you think is genuinely good, and why Your take: a client says our agent is "mostly right but wrong in ways that scare them." What do you do first? 2. We reply within 2-3 days — either "let's talk" or "not this time, here's why." No black hole. 3. We meet — 30-45 min call with the founder. We talk about your work, you ask us hard questions. If the chemistry isn't there, no hard feelings. 4. Problem-solving session (top 2-3 candidates) — we give you a real problem we're working on. You come back with how you'd approach it: your thinking, your trade-offs, your questions. We're not watching over your shoulder. We want to see how you think. 5. Decision within 2-3 days. If yes — you start when you're ready. Tomorrow, next week, after notice period. Your call.

🏢 Summary: Paid summer internship (July–September 2026) in production AI development, with possibility of extended cooperation. The role involves working on real client projects and the internal AI platform, contributing production-ready code across the full stack from the first week. Interns gain hands-on experience with modern web technologies, cloud infrastructure, and LLM-based agent systems. 🗂️ Requirements: Status studenta kierunku technicznego, Podstawy programowania w TypeScript lub Python, Własny ukończony projekt z działającym kodem, Umiejętność samodzielnego rozwiązywania problemów i pracy z dokumentacją, Realne używanie narzędzi AI w pracy programistycznej, Komunikatywny angielski B2+ 📃 Skills: TypeScript, Python, React, Node.js, PostgreSQL, AWS, LLM, RAG, MCP, Docker, Git, OpenAI, Anthropic, Claude, Cursor, Copilot 🏢 Description: Szczegóły: Branża: Architektura, Programowanie, Testowanie Stanowisko: Asystent, Praktykant / Stażysta Rodzaj umowy: Umowa zlecenie, Umowa o dzieło Wymiar pracy: Pełny etat, Część etatu, Dodatkowa / Sezonowa Charakter pracy: Stacjonarna, Hybrydowa Dodatkowe informacje: Status studenta / Praca dla młodzieży / Wymagane doświadczenie: Tak Szukamy stażysty/stażystki na płatny staż wakacyjny lipiec–wrzesień 2026 , z opcją przedłużenia współpracy po sezonie, jeśli z obu stron będzie chemia. Najchętniej widzimy studenta Politechniki Gdańskiej , ale nie zamykamy się na inne uczelnie — liczy się to, co potrafisz pokazać, nie indeks. Będziesz pracować nad realnymi projektami klientów AgentX i nad samą platformą. Nie chowamy stażystów do kąta na pisanie skryptów do migracji — od pierwszego tygodnia dostajesz konkretne zadanie, opiekuna i odpowiedzialność za swoje fragmenty kodu, który trafia na produkcję. Dotkniesz całego stacka: TypeScript, React, Node.js, Python, PostgreSQL, AWS , plus warstwa agentowa (LLM-y, RAG, MCP, tool calling, evale). Zobaczysz z bliska, jak wygląda "produkcyjnie" — testy, deployment, observability, prawdziwi userzy zgłaszający bugi. Nie wymagamy komercyjnego doświadczenia. Wymagamy, żebyś coś realnie kiedyś zbudował/a sam/a od początku do końca i potrafił/a o tym pogadać. Jak aplikować CV (krótkie, konkretne) Kilka zdań o swoim ulubionym własnym projekcie — co to było, co Cię w tym wciągnęło, co byś dziś zrobił/a inaczej Linki do kodu / dema / GitHuba / cokolwiek, co pokaże jak myślisz Wymagania: Otwarta głowa i chęć uczenia się. Produkcyjny development AI to coś więcej niż tutoriale — i ta różnica nas interesuje. Realne, świadome używanie narzędzi AI. Claude Code, Cursor, Copilot, agenci CLI — używasz ich, bo przyspieszają robotę, a nie dlatego, że są modne. Potrafisz powiedzieć, kiedy pomagają, a kiedy przeszkadzają. Własne projekty. MVP, hackathon, projekt zaliczeniowy, weekendowa zabawa, mały SaaS — cokolwiek, co samodzielnie doprowadziłeś/aś do działającej rzeczy. Najlepiej z linkiem do kodu albo dema. Samodzielność w rozwiązywaniu problemów. Czytasz dokumentację, próbujesz, debugujesz — i dopiero wtedy pytasz, konkretnie. Podstawy programowania w TypeScript lub Python (jednym z dwóch — drugiego się dobierzesz). Komunikatywny angielski (B2+) — dokumentacja, code review, czasem rozmowa z klientem. Status studenta (najchętniej PG, kierunki techniczne — Informatyka, ETI, AI&Robotyka, podobne). Mile widziane (ale nie wymagane): Doświadczenie z React / Node.js Pierwsze próby z LLM API (OpenAI, Anthropic, lokalne modele) Znajomość Dockera, Gita ponad podstawy Praca z PostgreSQL Oferujemy: Płatny staż wakacyjny lipiec–wrzesień 2026, stawka rynkowa do uzgodnienia po rozmowie technicznej. Realny kod produkcyjny od pierwszego tygodnia — nie "zadania szufladowe". Bezpośrednią pracę z seniorami robiącymi produkcyjne AI, nie z prezentacją PDF o "metodyce". Mentoring i code review — uczysz się tego, jak się to robi naprawdę, a nie jak wygląda na konferencji. Hybrydowy model pracy — biuro w Gdańsku, część dni zdalnie. Sami się dogadamy, co działa. Elastyczne godziny — jeśli masz sesję poprawkową albo inne zobowiązania, ułożymy harmonogram. Wolne weekendy. Bez wyjątków, bez "tylko ten jeden raz". Realna ścieżka po stażu — jeśli z obu stron jest chemia, przedłużamy współpracę (B2B, część etatu obok studiów — co Ci pasuje). Nie obiecujemy etatu w ciemno, ale traktujemy staż jako początek rozmowy, nie jako koniec. Sprzęt i licencje — w tym dostęp do płatnych narzędzi AI (Claude, Cursor, GitHub Copilot itp.). Czytanie każdego CV — odpowiadamy na każdą aplikację, niezależnie od decyzji. Benefity: zniżki na firmowe produkty i usługi kawa / herbata elastyczny czas pracy brak dress code'u spotkania integracyjne Aplikuj Informacje o firmie AgentX ( agentx.so ) to startup z Doliny Krzemowej, ale założyli go ludzie z Politechniki Gdańskiej. Po latach pracy w San Francisco zdecydowaliśmy, że chcemy budować dalej także stąd, skąd przyszliśmy — dlatego dziś mamy dwa biura: w SF i w Gdańsku. Na staż zapraszamy (na razie) do tego gdańskiego. Budujemy platformę do tworzenia i uruchamiania produkcyjnych agentów AI. Działamy w modelu "platforma + usługi" — z jednej strony rozwijamy infrastrukturę, na której powstają agenci, z drugiej sami dostarczamy klientom gotowe rozwiązania: od pierwszej rozmowy do działającego systemu na produkcji. AI traktujemy jako narzędzie, nie jako cel. Nie sprzedajemy "magii LLM-ów" — sprzedajemy software, który rozwiązuje konkretne problemy biznesowe, akurat z agentami w środku. Mały zespół, krótkie pętle decyzyjne, dwa kontynenty na Slacku. Realne projekty od pierwszego dnia — bez "zadań szufladowych", bez staży na ksero. Twój kod ląduje u prawdziwych userów.

🏢 Summary: Senior Frontend React Developer role focused on building enterprise-grade AI-native Next.js applications with complex state, real-time AI interactions, and scalable frontend architecture. The position involves owning frontend systems end-to-end, including UI design, performance optimization, accessibility, and production reliability. Engineers work closely with AI-driven products and modern tooling in a high-ownership environment. 🗂️ Requirements: 5+ years frontend engineering experience, 3+ years React experience, Modern TypeScript expertise, Production Next.js SSR experience, Knowledge of SSR, SSG, and CSR trade-offs, Complex state management experience, Experience building AI/LLM interfaces, Performance optimization and Core Web Vitals knowledge, Enterprise application development experience, Accessibility and localization knowledge, Security-conscious engineering approach, Daily use of AI coding agents, Clear technical communication skills 📃 Skills: React, TypeScript, Next.js, SSR, SSG, CSR, JavaScript, LLM, AI, CoreWebVitals, Accessibility, Localization, Security, ReactFlow, Highcharts, Node.js, Python, RAG, Codex, Claude, Copilot, GitHub 🏢 Description: About Shelf The enterprise is going agentic and we are creating a unique operating system for an automated future. Most AI agents break the moment they hit real business complexity. That’s why we built a platform that models a company's policies, workflows, and operational logic into an AI Data Model. Shelf enables AI Agents to reliably reason and deliver precise and reliable outcomes at scale. We already have what most AI startups are still trying to earn: Enterprise customers such as Glovo, Nespresso, and HelloFresh, real production data, and tens of thousands of users. Customers trust us with operational knowledge: Our platform is highly reliable and secure with SOC2, HIPAA-ready security practices, and mature integrations in place. Location – Warsaw, work from the office. Senior Frontend React Developer: This role is for a senior frontend engineer who can design and own business-critical user experiences for agentic AI products. We want someone who is strong technically, has strong UI judgment, communicates clearly, and has the taste to make complex product experiences simpler, faster, more trustworthy, and easier to evolve over time. Expect real ownership from frontend architecture through production quality. You will build production Next.js applications with complex state, real-time AI interactions, and multiple layers of enterprise functionality. The team is small enough for engineers to make real decisions. Career growth comes from ownership. Titles matter less than the scope you can carry. The people who grow fastest take responsibility for larger product surfaces, drive customer outcomes, and strive to develop better engineering practices. You solve ambiguous frontend problems by understanding the user need, shaping the right interaction model, then shipping, iterating, and keeping the experience healthy in production. We build AI-native. Engineers use Codex, Claude Code, and agents they build themselves. We invest in harness engineering through skills, CLIs, logs, traces, and orchestration. This is a role for someone in a high-growth chapter of their career, who wants to do the best work of their life, learn fast, and win as part of a team going all-in on a hard mission. What You Will Own Design and ship production Next.js SSR applications with complex state, high-load scenarios, and real-time AI interactions at scale Build interfaces for AI-powered features: streaming LLM responses, semantic search across millions of documents, interactive knowledge graphs, and agentic builders Architect component libraries and maintain the design system, ensuring reusability, accessibility, and consistent UX across the platform Deliver enterprise-grade functionality: localization, accessibility compliance, cross-browser support, and security Take full ownership after launch: monitor performance in production, optimize bundle sizes, instrument for Core Web Vitals, and ensure things scale gracefully Keep the bar high on code quality, testing, and craft through thoughtful code review and mentorship What Strong Performance Looks Like You turn vague product problems into shipped, well-reasoned interfaces that users trust Complex AI behavior feels legible and controllable to users because of how you built the UI Your components are reusable, accessible, and fast under real enterprise load You bring momentum. Work moves because you are on it What We Are Looking For Over 5 years of frontend engineering experience, including 3+ years specializing in React and modern TypeScript Production Next.js experience: SSR applications at scale, app router, server components, and the trade-offs between SSR, SSG, and CSR Complex state management for hard scenarios: real-time collaboration, optimistic updates, multi-tenant isolation, large-scale data sync Experience building AI/LLM interfaces: streaming token responses, chat UIs, semantic search, or similar real-time AI interactions High-load performance work: you monitor Core Web Vitals and know how to improve them under heavy traffic and large datasets Enterprise application depth: localization, accessibility, security, and compliance, you understand the complexity beyond "making it work" A security-conscious approach to engineering: you handle sensitive data carefully and think about the security implications of what you ship Strong craft and product instinct: you don't wait for perfect designs, you spot UX issues and propose solutions, and you're never satisfied with "good enough" AI-native working style. You already use AI coding agents daily and are eager to push the boundaries of harness engineering Clear communication. You articulate design decisions and technical trade-offs clearly, verbally and in writing Strong Plus Experience with React Flow, Highcharts, or other complex data-visualization libraries Hands-on experience with vector search UIs, RAG interfaces, or generative UI Understanding of Node.js/Python: you can read backend code and contribute to API design discussions Built or contributed to design systems or open-source component libraries How We Evaluate Fit We care more about craft, ownership, and the ability to make complex AI feel trustworthy than a perfect match to every library on paper. If you are the kind of engineer who can take a messy, complex enterprise problem and turn it into an interface people trust, we want to talk. What Shelf Offers: B2B contract Company Stock Options Hardware: MacBook Pro Modern technical stack. Develop open-source software A strong AI-native engineering environment with modern tools and room to experiment, including Claude Code, OpenAI Codex, and GitHub Copilot Why Shelf Becoming one of the defining companies of the AI age is a hard plan, and our leadership team has the rare mix of deep AI, knowledge-management, and enterprise SaaS experience to actually execute it We have raised over $60 million in funding; our investors include Tiger Global, Insight Partners, Base10, and others Recognized by Gartner as a Cool Vendor, with high-velocity growth powered by the most innovative product in our category We love our customers and our customers love us. Ask a Shelf customer why, and they'll tell you it's our innovative capabilities and rock-solid reliability, that they enjoy working with our people, and most of all, the improvements they see in their business KPIs We're building fast across three hubs: our New York HQ and our Product and Engineering centers in Warsaw and Lviv

🏢 Summary: Senior Software Engineer role focused on designing and delivering scalable, distributed payment platform solutions in a cloud-native environment. The position combines hands-on backend development in .NET with technical leadership, architectural ownership, and mentoring responsibilities. A key aspect of the role is introducing and leading agent-based (AI-driven) engineering workflows across the SDLC. 🗂️ Requirements: 5+ years of software engineering experience (Back-End or Full-Stack), Experience with .NET and C#, Experience with cloud platforms (Azure, AWS, or GCP), Experience with Docker and .NET 6+, Experience building scalable, low-latency, event-driven distributed systems, Experience designing and integrating RESTful and gRPC APIs, Experience with microservices and cloud-native architectures, Experience with SQL databases, Experience in payments or financial systems, Hands-on experience with agentic development tools (e.g., Claude Code, Copilot Workspace), Ability to evaluate and validate AI-generated code, Experience working in Agile Scrum environments 📃 Skills: C#, .NET, SQL, SQLServer, Azure, AWS, GCP, Docker, REST, gRPC, Microservices, Cloud, Terraform, Postgres, VueJS, React, Jira, Confluence, Claude, Copilot 🏢 Description: Overview Permanent, full-time, hybrid Connecting clients to markets – and talent to opportunity. With 4,300 employees and over 400,000 retail and institutional clients from more than 80 offices spread across five continents, we’re a Fortune-100, Nasdaq-listed provider, connecting clients to the global markets – focusing on innovation, human connection, and providing world-class products and services to all types of investors. Whether you want to forge a career connecting our retail clients to potential trading opportunities, or ingrain yourself in the world of institutional investing, The StoneX Group is made up of four segments that offer endless potential for progression and growth. Business Segment Overview: A Swift-accredited service bureau and member, our Payments division provides NGOs, institutions and non-profits the ability to make a local difference, globally – with transparent pricing across 180+ countries and 140+ currencies. Technology Ecosystem: Back End: C#, .NET Database: SQL Server Cloud: Azure Responsibilities Position Purpose: StoneX Payments is looking for a Senior Software Engineer to design, develop and implement software applications that make up key components of our platforms. You will deliver high-quality software that is aligned with customer needs and business goals. You will be expected to set standards in a highly modernize and distributed environment. You will be responsible for the technical excellence and approach taken by less experienced team members, including providing guidance and oversight, planning and estimation, analyzing software performance and configuration systems, peer code reviews and documentation, and the deployment and integration of new software from technology standards you set. You will collaborate with product owners in an agile scrum to scope, develop and deploy solutions, continuously iterating to ensure that new features are adding value to our customers. You are expected to conduct design and code reviews within the engineering team and vetting designs across your teams with business initiatives. You are expected to get into the details of our solutions, lead implementation, and take ownership of the team’s output. Come help us develop the next-generation payments platform! The ideal candidate is passionate about growing their skills and building complex distributed systems. Primary duties will include: Execute on the software development life cycle (SDLC) for the team including estimating, analysis, code design, development, testing, debugging, and maintenance. Implement engineering standards, best practices, and quality assurance procedures. Work closely with product owners to understand product requirements and translate them into technical stories. Provide technical expertise and insight to analyze complex requirements and break down features and initiatives into tasks. Take responsibility for the quality of the applications as well as its alignment with technology and product goals. Review and give constructive feedback on code. Identify recurring issues and opportunities to improve engineering process and coding standards. Lead the execution of software solutions along with monitoring and supporting tools to ensure the software works well in the operating environment. Actively participate in strategic implementation regarding technology solutions and platform architecture Mentor and grow less experienced engineers. Forward thinking on modern technology and the payments industry. Agentic Development Leadership: This is the major differentiator of the role. Introduce, design, and operationalize agent-based engineering workflows across the SDLC. Use tools such as Claude Code, capable of repository-wide reasoning, automated refactoring, debugging, and commit generation to accelerate engineering throughput. Build “agent-ready” codebases through modular design, clean documentation, and comprehensive test coverage — key enablers of successful agentic development. Actively contribute to and/or lead the new agentic development team for Payments (e.g., new wallet solution POC). Evaluate AI-generated code for quality, correctness, architectural alignment, and security. Develop internal best practices, training materials, and standards for agent-accelerated engineering. Qualifications To land this role you will need : 5+ years software engineering experience, primarily Back-End or Full-Stack. Experience with .NET and Cloud platforms (Azure/AWS/GCP). Experience working with Docker, .NET 6+, C#. Experience designing and writing robust software for highly scalable, low-latency, event driven, distributed platforms. Strong experience with object-oriented programming and design, including C# or any other programming languages. Experience designing, implementing, and integrating with RESTful and gRPC APIs. Experience with modern architectures and practices including microservices, cloud computing, micro frontends, and domain driven design. Experience with financial products, specifically payments. Experience with Jira and Confluence. Able to work in a positive team culture with a strong sense of accountability and collaboration. Able to balance incoming requirements with a focus on tactical execution. Excellent coding skillset and peer code review. Excellent verbal and written communication skills. Excellent analytical and problem-solving skills. Excellent skills working in a distributed Lean Agile Scrum Team. Deep understanding of modern cloud native technology with microservice/microsite design patterns. What makes you stand out: Experience in SaaS, Payments, FinTech, or E:commerce. Experience with IaC, specifically Terraform. Experience with microservice design pattern, specifically Twelve-Factor. Experience with document databases. Experience working with VueJs/React, and Postgres. Agentic Development Skills: (What makes this role unique) Hands-on experience with agentic development tools such as Claude Code, Copilot Workspace, or equivalent. Ability to orchestrate multi-agent workflows (refactoring, debugging, dependency updates, code generation). Deep understanding of how design quality affects agent output (modularity, documentation, test coverage). Experience evaluating and validating AI-generated code. Ability to build frameworks, patterns, and tooling for agent-powered engineering at scale. Working environment: FTE (UoP). Hybrid at ul. Mogilska 35 – we have private parking for employees.

🏢 Summary: Backend Engineer role focused on building and scaling the core architecture behind AI Agents, including reasoning layers, RAG systems, and high-volume conversational infrastructure. The position involves designing agentic orchestration, modernizing legacy systems, and integrating AI capabilities into scalable microservices running in production. You will work hands-on with LLM integrations, vector databases, and cloud-native infrastructure to support millions of daily conversations. 🗂️ Requirements: 6+ years backend development experience, Strong hands-on expertise in Node.js, Strong hands-on expertise in TypeScript, Experience with async programming, queues, and streams, Experience with real-time communication (WebSockets, service-to-service messaging), Commercial experience implementing RAG and Agentic systems in production, Experience with Function Calling and LLM integrations, Deep understanding of context management and multi-turn conversations, Experience with SQL databases (PostgreSQL), Experience with NoSQL databases (Elasticsearch), Experience with Vector Databases and embeddings, Experience with Google Cloud Platform, Experience with Kubernetes, Ability to design and maintain RESTful APIs, Experience working with microservices and scalable systems 📃 Skills: Node.js, TypeScript, PostgreSQL, Redis, Elasticsearch, Pinecone, pgvector, GCP, Kubernetes, Docker, LangGraph, LLMs, RAG, MCP, PubSub, WebSockets, SSE, Webhooks, Prometheus, Grafana, Vitest, Supertest, Playwright, Go, ETL, Microservices, Concurrency, Async, Streams, Queues, GitHubActions 🏢 Description: About your team You’ll join AI Engines – the team building the backend “brain” of AI Agents in Text App. These aren’t your average scripted bots. Our AI Agents understand context, communicate naturally, and take meaningful actions: from digging through the Knowledge Hub to answer customer queries, to guiding human agents, or triggering automations in third-party tools via Copilot. To make this happen, we need to design highly scalable backend systems capable of handling millions of conversations daily. We build the APIs, develop the reasoning layers, and continuously push the boundaries of what our agents can actually do. You will be responsible for: Hands-on building, scaling, and maintaining the core backend architecture (Vector Database, AI Engines, Knowledge Hub, etc.). Designing and implementing an Agentic reasoning and orchestration layer using Skills and tool calling (a core building block of our architecture). Modernizing the core by taking full ownership of migrating legacy implementations into our modern, highly scalable AI ecosystem. Collaborating with our AI researchers to experiment with, validate, and confidently push new AI features straight to production. Mastering Context Engineering & R&D by moving way beyond basic prompt engineering. You'll be experimenting with and optimizing how our agents communicate with LLMs (taking full ownership of multi-turn conversations, tool calling, advanced RAG integrations, system prompt design, and history management). Designing RESTful APIs and service integrations for AI and data-heavy use cases, while migrating legacy implementations to a modern ecosystem. Integrating AI Agents with MCP servers, shaping how they interact with external ecosystems. Setting the standard by taking an active part in architecture discussions, code reviews, and technical decision-making, while bringing an extreme ownership and "fast flagging" mindset to the team. You may be a good fit for this role if you: Have 6+ years of experience in backend development, with strong, recent, hands-on expertise in Node.js and TypeScript in recent projects . We need someone who is fluent in async programming, queues, and streams, and can jump into our codebase on Day 1. Have hands-on experience with real-time communication (WebSockets, async service-to-service messaging). Have proven commercial experience building AI-driven features . You don't just know the concepts—you’ve actively implemented RAG, Function Calling, and Agentic systems in production. A deep understanding of Context Engineering. You know that it’s no longer just about "writing good prompts." You have proven experience managing context windows, multi-turn conversation history, and tool calling within Agentic or RAG ecosystems. Have a solid grasp of database ecosystems, including SQL (Postgres) , NoSQL (Elasticsearch) , and Vector Databases (e.g., Pinecone, pgvector), along with the mechanics of embeddings. Know how to run and scale services on Google Cloud Platform and Kubernetes. Enjoy solving complex technical challenges in microservices, concurrency, and performance optimization. Bonus if you also: Experience with Go (Golang) is a strong plus. Have experience building Data Pipelines or ETL processes. Previous work on SaaS products, low-code/no-code platforms, or workflow automation. Our Tech Stack: (Let’s be transparent: while we value curiosity and a growth mindset, solid hands-on experience with Node.js and TypeScript is a strict requirement for this role. We are happy to give you time to learn our specific AI frameworks and databases on the go, as long as your core backend skills are top-notch.) Core (Must-have) : Node.js, TypeScript Databases : PostgreSQL, Redis, ElasticSearch Scalability & communication : PubSub, Webhooks, SSE AI-related : LLMs, LangGraph, Function Calling, Context Compression, MCP (Model Context Protocol) Infrastructure & deployment : Docker, GitHub Actions, Prometheus, Grafana Testing & reliability : Vitest, Supertest, Playwright How we work We’re a hybrid team – remote when it makes sense, onsite when it matters most. Once per quarter, your whole team spends 5 working days together at our Wrocław office – a time for focused execution, unblocking work, and driving key outcomes. Our office is open year-round – drop by anytime. Contract: B2B (self-employed). You’ll need a registered business in selected EU countries — either already set up or possible to register in your country . Please apply only if this works for you.

🏢 Summary: Senior Backend Engineer role focused on building and scaling the core AI backend powering advanced AI Agents, including reasoning layers, RAG systems, and real-time integrations. The position involves designing scalable architectures, implementing agentic orchestration with tool calling, and modernizing legacy systems into a high-performance AI ecosystem. You will work hands-on with Node.js and TypeScript to deliver production-ready AI-driven features handling millions of conversations. 🗂️ Requirements: 6+ years backend development experience, Strong hands-on Node.js experience, Strong hands-on TypeScript experience, Fluency in async programming, queues, streams, Experience with WebSockets and async messaging, Commercial experience implementing RAG systems, Experience with Function Calling in production, Experience building Agentic systems, Context window and multi-turn conversation management, Experience with SQL and NoSQL databases, Experience with Vector Databases and embeddings, Experience with GCP and Kubernetes, Experience with microservices architecture, Experience with Docker-based deployments 📃 Skills: Node.js, TypeScript, PostgreSQL, Redis, Elasticsearch, Pinecone, pgvector, GCP, Kubernetes, Docker, PubSub, WebSockets, SSE, LLMs, LangGraph, RAG, MCP, GitHub, Prometheus, Grafana, Vitest, Supertest, Playwright, Go 🏢 Description: About your team You’ll join AI Engines – the team building the backend “brain” of AI Agents in Text App. These aren’t your average scripted bots. Our AI Agents understand context, communicate naturally, and take meaningful actions: from digging through the Knowledge Hub to answer customer queries, to guiding human agents, or triggering automations in third-party tools via Copilot. To make this happen, we need to design highly scalable backend systems capable of handling millions of conversations daily. We build the APIs, develop the reasoning layers, and continuously push the boundaries of what our agents can actually do. You will be responsible for: Hands-on building, scaling, and maintaining the core backend architecture (Vector Database, AI Engines, Knowledge Hub, etc.). Designing and implementing an Agentic reasoning and orchestration layer using Skills and tool calling (a core building block of our architecture). Modernizing the core by taking full ownership of migrating legacy implementations into our modern, highly scalable AI ecosystem. Collaborating with our AI researchers to experiment with, validate, and confidently push new AI features straight to production. Mastering Context Engineering & R&D by moving way beyond basic prompt engineering. You'll be experimenting with and optimizing how our agents communicate with LLMs (taking full ownership of multi-turn conversations, tool calling, advanced RAG integrations, system prompt design, and history management). Designing RESTful APIs and service integrations for AI and data-heavy use cases, while migrating legacy implementations to a modern ecosystem. Integrating AI Agents with MCP servers, shaping how they interact with external ecosystems. Setting the standard by taking an active part in architecture discussions, code reviews, and technical decision-making, while bringing an extreme ownership and "fast flagging" mindset to the team. You may be a good fit for this role if you: Have 6+ years of experience in backend development, with strong, recent, hands-on expertise in Node.js and TypeScript in recent projects . We need someone who is fluent in async programming, queues, and streams, and can jump into our codebase on Day 1. Have hands-on experience with real-time communication (WebSockets, async service-to-service messaging). Have proven commercial experience building AI-driven features . You don't just know the concepts—you’ve actively implemented RAG, Function Calling, and Agentic systems in production. A deep understanding of Context Engineering. You know that it’s no longer just about "writing good prompts." You have proven experience managing context windows, multi-turn conversation history, and tool calling within Agentic or RAG ecosystems. Have a solid grasp of database ecosystems, including SQL (Postgres) , NoSQL (Elasticsearch) , and Vector Databases (e.g., Pinecone, pgvector), along with the mechanics of embeddings. Know how to run and scale services on Google Cloud Platform and Kubernetes. Enjoy solving complex technical challenges in microservices, concurrency, and performance optimization. Bonus if you also: Experience with Go (Golang) is a strong plus. Have experience building Data Pipelines or ETL processes. Previous work on SaaS products, low-code/no-code platforms, or workflow automation. Our Tech Stack: (Let’s be transparent: while we value curiosity and a growth mindset, solid hands-on experience with Node.js and TypeScript is a strict requirement for this role. We are happy to give you time to learn our specific AI frameworks and databases on the go, as long as your core backend skills are top-notch.) Core (Must-have) : Node.js, TypeScript Databases : PostgreSQL, Redis, ElasticSearch Scalability & communication : PubSub, Webhooks, SSE AI-related : LLMs, LangGraph, Function Calling, Context Compression, MCP (Model Context Protocol) Infrastructure & deployment : Docker, GitHub Actions, Prometheus, Grafana Testing & reliability : Vitest, Supertest, Playwright How we work We’re a hybrid team – remote when it makes sense, onsite when it matters most. Once per quarter, your whole team spends 5 working days together at our Wrocław office – a time for focused execution, unblocking work, and driving key outcomes. Our office is open year-round – drop by anytime. Contract: B2B (self-employed). You’ll need a registered business in selected EU countries — either already set up or possible to register in your country . Please apply only if this works for you.

🏢 Summary: Frontend Engineer role focused on building and owning the UI layer of production-ready AI products for B2B clients using TypeScript and React. The position involves developing performant, maintainable interfaces, integrating REST APIs, and handling real-time data flows in close collaboration with backend engineers. This is a hands-on role working on client-facing AI systems where usability and reliability are critical. 🗂️ Requirements: 3–5 years of experience building production frontend applications, Strong experience with TypeScript and React, Experience integrating REST APIs, Experience handling asynchronous UI states, Ability to manage authentication, loading, and streaming states, Experience with SSE or WebSockets, Ability to read and debug Python and FastAPI code 📃 Skills: TypeScript, React, Vite, REST, SSE, WebSockets, Python, FastAPI, Tailwind, shadcn 🏢 Description: About Agentica Agentica is an AI automation startup that designs and deploys custom AI products and agents for B2B clients worldwide. The company builds production-ready AI systems that automate and replace manual business processes across helpdesks, internal tools, e-commerce, production, and other high-friction areas. Its team delivers practical agentic AI solutions for clients ranging from cybersecurity software distributors to global Web3 companies. The Role You’ll own the frontend layer of AI products and client projects, working mainly with TypeScript and React. This is hands-on work on production systems where usability, performance, and reliability matter. You’ll work closely with the tech team and be responsible for shipping clean, maintainable UI code ready for client use. What You’ll Do Build and maintain frontend applications using TypeScript, React, and Vite. Collaborate with backend engineers to integrate REST APIs and manage async data flows. Prototype new interfaces with clients in early stages. Implement clean, extensible component architectures. Handle auth states, loading states, and streaming data (SSE / WebSockets). Read and debug Python / FastAPI backends when needed. Guide coding agents while ensuring code quality. What We’re Looking For Clear communication and strong ownership. AI-first mindset and ability to learn quickly. 3–5 years building production frontend applications. Strong TypeScript and React experience. Experience integrating APIs and handling async UI states. Comfortable reading Python / FastAPI code. Nice to Have Tailwind CSS or component libraries (e.g., shadcn/ui). B2B SaaS or enterprise product experience. What We Offer Attractive salary PLN 12,000–20,000 depending on experience. High-ownership projects with real technical depth and steep learning curves. Early-stage leverage: join while the company is scaling fast and shape how it grows. Fully remote or hybrid from our office in central Warsaw. Flexible working hours built around output, not presence. A senior, technically sharp team with hands-on AI and software delivery experience. Apply now and build leading AI products. Join a team that cares about quality, ownership, and real client impact.

🏢 Summary: Senior Full-Stack Engineer role in an AI-enabled SDLC environment, responsible for turning AI-generated prototypes into secure, performant, and production-ready features. The position involves end-to-end ownership across backend and frontend, with accountability for code quality, scalability, and reliability in enterprise SaaS products. Engineers act as technical guardrails, ensuring sound architecture, data integrity, and long-term maintainability. 🗂️ Requirements: 5+ years of experience building and shipping production software as a full-stack engineer, Strong proficiency in Python and experience with a mature Python web framework (e.g. Django), Strong proficiency in React and TypeScript, Experience designing and maintaining REST APIs, Experience with relational data modelling, Ability to review code critically and identify logic flaws, performance issues, and scalability risks, Experience owning features in production and fixing live issues, Ability to ensure security, performance, and data integrity in enterprise applications, Fluent English communication skills 📃 Skills: Python, Django, React, TypeScript, REST, SQL, APIs, DataModeling, Performance, Security, AI, Claude 🏢 Description: About Vatix Vatix is a fast-growing SaaS company founded in London and Kraków in 2019. We're on a mission to bring a fresh, user-centric approach to the world of Governance, Risk, and Compliance software — with a particular focus on Health & Safety and Operational Excellence. Today, over 800 businesses and government organisations around the world trust our platform to protect their people, streamline safety workflows, and drive operational performance. We're not VC-owned, and we're not chasing vanity metrics. Instead, we're building a long-term, sustainable company that's focused on solving real-world problems and becoming one of the most consequential players in our category. Our customers include industry leaders such as Cambridge University, Siemens, Intel, and major government departments — organisations that depend on us for mission-critical systems. At Vatix, you'll be working across a diverse product suite that spans web applications, mobile apps, IoT-enabled safety devices, and data platforms. That means a rare opportunity to learn and grow across a range of technologies — all while being supported by a collaborative team that values quality, simplicity, and mentorship. The role We're hiring senior full-stack engineers who can own the engineering judgement behind our product. Our SDLC is heavily AI-enabled: a lot of the time you'll be handed a working prototype rather than starting from a blank file. Your job is to make sure the logic and performance behind it are genuinely sound before it ships — and to own it in production once it does, including fixing the bugs. This is not a role where AI does the thinking for you. It's the opposite: AI accelerates the build, and you are the guardrail. You're the senior engineer who decides whether something is correct, performant, secure, and maintainable enough to put in front of enterprise customers — and who's accountable when it's live. What you'll do Take AI-generated prototypes from "it works on the happy path" to production-ready — interrogate the logic, find the edge cases, validate performance, and harden what's weak. Don't worry about AI slop. Prototype is there for Proof-of-concept. You are responsible for final solution that can but doesn't have to use components AI created Own features in production : you ship it, you own the bugs, you fix them. No throwing things over a wall. Act as the guardrail on AI-generated output — reviewing it the way you'd review a strong-but-junior engineer's work, and holding it to real engineering standards. Work across the stack in Python on the backend (REST APIs, data modelling, integrations) and React + TypeScript on the frontend. Care about the things that matter to enterprise customers: security, data integrity, performance, and a genuinely good user experience. Raise the engineering bar — review thoughtfully, mentor, and improve how the team builds with AI in the loop. How we work Our development process is heavily enhanced by AI, and we lean into it. But our engineers still own every decision. AI writes a lot of the first draft; people decide what's right, catch what's wrong, and are accountable for what ships. If you're excited by an AI-enabled SDLC where your judgement is the most valuable thing in the room — not threatened by it — you'll fit well here. We mainly use Claude Code with many skills and guidelines on top of it. What we're looking for 5+ years building and shipping production software as a full-stack engineer. Strong Python (we use Django; deep experience with any mature Python web framework transfers well) and strong React + TypeScript . A sharp eye for what's wrong with code that looks right — you can read an implementation and spot the broken logic, the N+1 query, the missing edge case, the thing that won't scale. Comfort with relational data modelling, designing clean REST APIs, and reasoning about performance and scale. Genuine ownership instinct — you stand behind what you ship and fix it when it breaks, rather than treating production as someone else's problem. Sound judgement about trade-offs: when something is good enough to ship, when it isn't, and where correctness is non-negotiable. Openness to an AI-enabled SDLC — you treat AI as a powerful tool you direct and verify, not as a replacement for engineering judgement. Clear communication in English, and the instinct to ask rather than guess. Nice to have Experience in B2B / enterprise SaaS, especially with security, compliance, or data-heavy products. Working with embedded analytics, data warehousing, or BI tooling. AI initiatives that improved velocity of the entire team Vatix is an equal opportunity employer. We welcome applicants from all backgrounds.

🏢 Summary: Hands-On Engineering Manager role focused on building and shipping AI-native, agentic banking products that operate across voice, chat, and digital channels. The position involves architecting low-latency distributed backend systems, orchestrating multi-agent LLM workflows, and leading a high-performance engineering team while remaining deeply hands-on. The goal is to deliver production-grade AI systems that autonomously power real-time financial customer experiences. 🗂️ Requirements: 8+ years backend engineering experience, Experience building distributed systems, Experience with low-latency systems (voice, telephony, streaming, chat), 3+ years working with LLM-powered or AI-driven systems in production, Hands-on experience integrating systems with LLMs, 2+ years engineering management or technical leadership experience, Experience designing and orchestrating agentic workflows, Proficiency in Typescript and/or at least two backend languages, Strong understanding of distributed systems, concurrency, reliability, Experience deploying AI systems in cloud environments, Experience building high-concurrency, fault-tolerant systems, Experience implementing observability, monitoring, and testing for production systems, Experience ensuring security and safe handling of financial data 📃 Skills: Typescript, Node.js, Go, Java, Rust, LLM, AgenticAI, DistributedSystems, Concurrency, Telephony, Streaming, Chat, APIs, Cloud, Observability, Monitoring, Testing, Security, ReinforcementLearning, MultiAgentSystems 🏢 Description: Banking is being reimagined—and customers expect every interaction to be easy, personal, and instant. We are building a universal banking assistant that millions of U.S. consumers can use to transact across all financial institutions and, over time, autonomously drive their financial goals. Powered by our proprietary BankGPT platform, this assistant is positioned to displace age-old legacy systems within financial institutions and own the end-to-end CX stack, unlocking a $200B opportunity and potentially replacing multiple publicly traded companies. Ultimately, our mission is to drive financial well-being for millions of consumers. With over two-thirds of Americans living paycheck to paycheck, 50% holding less than $500 in savings, and only 17% financially literate, we aim to put financial well-being on autopilot to help solve this problem.About the Role We are building AI-native, agentic products that redefine how customers interact with financial institutions across voice, chat, and digital channels. We are looking for a Hands-On Engineering Manager – Agentic AI Products who operates with an AI-first mindset, has deep backend systems experience, and is comfortable orchestrating multiple AI agents to ship production-grade systems. This role requires someone who: Has built complex distributed backend systems Understands low-latency architectures (voice, telephony, streaming, chat) Is fluent in modern agentic AI engineering Thinks like a founder Leads by building Raises the engineering bar You will architect, review, code, debug, and ship along with building your high performance engineering team. What You'll Do 1. Lead with an AI-First Engineering Mindset Drive AI-first thinking across product architecture and execution. Embed LLMs, multi-agent systems, and structured reasoning into customer-facing workflows. Champion agentic engineering principles across your team. Evaluate and adopt emerging AI capabilities pragmatically and responsibly. Raise the quality bar for AI-generated and human-written code alike. 2. Build and Orchestrate Agentic Systems Architect and implement systems that coordinate multiple AI agents with memory, planning, reflection, and tool use. Be hands-on in coding, agent loop design, evaluation, and reinforcement strategies. Actively participate in the code base Design orchestration layers that convert AI reasoning into reliable execution. Build control frameworks around LLMs for grounding, safety, and deterministic behavior. Develop evaluation pipelines to ensure agents meet production standards. 3. Own Low-Latency, High-Concurrency Backend Systems Design distributed backend systems serving real-time voice and chat interactions. Optimize latency-sensitive systems across telephony, streaming, and API layers. Build event-driven architectures that handle high concurrency and fault tolerance. Implement state management and memory layers for conversational agents. Drive reliability, failover, and graceful degradation strategies. 4. Ship Production-Ready AI Products Ensure AI-generated outputs translate into robust, testable, production-quality code. Maintain high standards for observability, monitoring, and debugging. Build automation and testing strategies for agent-based systems. Ensure security, compliance, and safe handling of financial data. Create durable systems that scale with increasing AI complexity. Lead by example in adopting AI tooling (Cursor, Claude Code, LLM automation) to improve engineering velocity and code quality 5. Operate Like a Founder Demonstrate extreme ownership across product, architecture, and delivery. Drive clarity in ambiguous problem spaces. Move quickly without compromising engineering rigor. Build and grow a high-performance team with bias to action. Set culture around accountability, urgency, and craftsmanship. Required Qualifications 8+ years of backend engineering experience building distributed systems. Strong experience with low-latency systems such as: Voice / telephony platforms Real-time streaming systems Chat or messaging architectures 3+ years working with LLM-powered or AI-driven systems in production Hands on experience building systems that interface with LLMs. 2+ years experience in engineering management or technical leadership with a proven ability to grow and mentor engineers Hands-on experience designing and orchestrating agentic workflows. Strong proficiency in Typescript and/or at least two backend languages (Node.js, Go, Java, Rust etc) Deep understanding of distributed systems, concurrency, and reliability. Experience managing engineers while remaining deeply hands-on. Experience deploying AI systems in cloud environments. Product Mindset: You care deeply about the product experience Strongly Preferred Experience building AI-native customer-facing products. Experience in Fintech or regulated environments. Familiarity with multi-agent architectures and reasoning frameworks. Experience with reinforcement learning or adaptive optimization loops. Experience building structured evaluation and monitoring for AI agents. Who You Are You care deeply about engineering quality and raise the bar for everyone around you. You demonstrate AI-first approaches when solving problems. You move fast and take ownership beyond your scope. You operate with founder-level urgency and accountability. You build teams that execute with discipline and craftsmanship. You are comfortable orchestrating multiple AI agents to produce production-ready outcomes. What Makes This Role Matters? Agentic engineering is changing how products are built. This role defines how: AI systems reason in real time Voice and chat agents operate under latency constraints Financial workflows become autonomous yet safe Multiple AI agents collaborate to produce deterministic, high-quality outcomes You will lead the engineering effort that transforms AI from an assistant into a production-grade system embedded deeply into customer experiences. We value in-person time for planning, problem-solving, and connection. Team members in this role must live within commuting distance of our Palo Alto or San Francisco office hub and this is an -site role. Compensation: Base Salary is expected to be between $200,000 - $240,000, plus performance bonus and equity options Exact compensation may vary based on skills and location. The base salary range represents the minimum and maximum of the salary range for this position based at our Palo Alto headquarters. The actual base salary offered for this position will depend on numerous factors, including individual proficiency, anticipated performance, and the location of the selected candidate. Our base salary is just one component of out competitive total rewards package, which also includes equity awards (a new hire grant), competitive health and wellness benefits. What We Offer 100% paid health, dental & vision care 401(k) match & financial wellness perks Discretionary PTO + paid parental leave Mental health, wellness & family benefits A mission-driven team shaping the future of banking At Interface.ai, we are committed to providing an inclusive and welcoming environment for all employees and applicants. We celebrate diversity and believe it is critical to our success as a company. We do not discriminate on the basis of race, color, religion, national origin, age, sex, gender identity, gender expression, sexual orientation, marital status, veteran status, disability status, or any other legally protected status. All employment decisions at Interface.ai are based on business needs, job requirements, and individual qualifications. We strive to create a culture that values and respects each person's unique perspective and contributions. We encourage all qualified individuals to apply for employment opportunities with Interface.ai and are committed to ensuring that our hiring process is inclusive and accessible.

🏢 Summary: Hands-On Engineering Manager role focused on building and orchestrating AI-native, agentic systems for real-time voice and chat in banking. The position combines deep backend distributed systems expertise with LLM-driven multi-agent architectures to deliver low-latency, production-grade AI products. You will lead a high-performance team while remaining hands-on in architecting and shipping scalable, reliable AI systems. 🗂️ Requirements: 8+ years backend engineering experience in distributed systems, Experience building low-latency systems (voice, telephony, streaming, chat), 3+ years working with LLM-powered or AI-driven systems in production, Hands-on experience integrating and orchestrating LLMs, 2+ years engineering management or technical leadership experience, Strong proficiency in TypeScript and/or at least two backend languages (Node.js, Go, Java, Rust), Deep understanding of distributed systems, concurrency, and reliability, Experience deploying AI systems in cloud environments, Experience designing agentic workflows and multi-agent systems 📃 Skills: TypeScript, Node.js, Go, Java, Rust, LLMs, AgenticAI, DistributedSystems, Concurrency, Telephony, Streaming, APIs, Cloud, ReinforcementLearning, Monitoring, Observability 🏢 Description: Banking is being reimagined—and customers expect every interaction to be easy, personal, and instant. We are building a universal banking assistant that millions of U.S. consumers can use to transact across all financial institutions and, over time, autonomously drive their financial goals. Powered by our proprietary BankGPT platform, this assistant is positioned to displace age-old legacy systems within financial institutions and own the end-to-end CX stack, unlocking a $200B opportunity and potentially replacing multiple publicly traded companies. Ultimately, our mission is to drive financial well-being for millions of consumers. With over two-thirds of Americans living paycheck to paycheck, 50% holding less than $500 in savings, and only 17% financially literate, we aim to put financial well-being on autopilot to help solve this problem.About the Role We are building AI-native, agentic products that redefine how customers interact with financial institutions across voice, chat, and digital channels. We are looking for a Hands-On Engineering Manager – Agentic AI Products who operates with an AI-first mindset, has deep backend systems experience, and is comfortable orchestrating multiple AI agents to ship production-grade systems. This role requires someone who: Has built complex distributed backend systems Understands low-latency architectures (voice, telephony, streaming, chat) Is fluent in modern agentic AI engineering Thinks like a founder Leads by building Raises the engineering bar You will architect, review, code, debug, and ship along with building your high performance engineering team. What You'll Do 1. Lead with an AI-First Engineering Mindset Drive AI-first thinking across product architecture and execution. Embed LLMs, multi-agent systems, and structured reasoning into customer-facing workflows. Champion agentic engineering principles across your team. Evaluate and adopt emerging AI capabilities pragmatically and responsibly. Raise the quality bar for AI-generated and human-written code alike. 2. Build and Orchestrate Agentic Systems Architect and implement systems that coordinate multiple AI agents with memory, planning, reflection, and tool use. Be hands-on in coding, agent loop design, evaluation, and reinforcement strategies. Actively participate in the code base Design orchestration layers that convert AI reasoning into reliable execution. Build control frameworks around LLMs for grounding, safety, and deterministic behavior. Develop evaluation pipelines to ensure agents meet production standards. 3. Own Low-Latency, High-Concurrency Backend Systems Design distributed backend systems serving real-time voice and chat interactions. Optimize latency-sensitive systems across telephony, streaming, and API layers. Build event-driven architectures that handle high concurrency and fault tolerance. Implement state management and memory layers for conversational agents. Drive reliability, failover, and graceful degradation strategies. 4. Ship Production-Ready AI Products Ensure AI-generated outputs translate into robust, testable, production-quality code. Maintain high standards for observability, monitoring, and debugging. Build automation and testing strategies for agent-based systems. Ensure security, compliance, and safe handling of financial data. Create durable systems that scale with increasing AI complexity. Lead by example in adopting AI tooling (Cursor, Claude Code, LLM automation) to improve engineering velocity and code quality 5. Operate Like a Founder Demonstrate extreme ownership across product, architecture, and delivery. Drive clarity in ambiguous problem spaces. Move quickly without compromising engineering rigor. Build and grow a high-performance team with bias to action. Set culture around accountability, urgency, and craftsmanship. Required Qualifications 8+ years of backend engineering experience building distributed systems. Strong experience with low-latency systems such as: Voice / telephony platforms Real-time streaming systems Chat or messaging architectures 3+ years working with LLM-powered or AI-driven systems in production Hands on experience building systems that interface with LLMs. 2+ years experience in engineering management or technical leadership with a proven ability to grow and mentor engineers Hands-on experience designing and orchestrating agentic workflows. Strong proficiency in Typescript and/or at least two backend languages (Node.js, Go, Java, Rust etc) Deep understanding of distributed systems, concurrency, and reliability. Experience managing engineers while remaining deeply hands-on. Experience deploying AI systems in cloud environments. Product Mindset: You care deeply about the product experience Strongly Preferred Experience building AI-native customer-facing products. Experience in Fintech or regulated environments. Familiarity with multi-agent architectures and reasoning frameworks. Experience with reinforcement learning or adaptive optimization loops. Experience building structured evaluation and monitoring for AI agents. Who You Are You care deeply about engineering quality and raise the bar for everyone around you. You demonstrate AI-first approaches when solving problems. You move fast and take ownership beyond your scope. You operate with founder-level urgency and accountability. You build teams that execute with discipline and craftsmanship. You are comfortable orchestrating multiple AI agents to produce production-ready outcomes. What Makes This Role Matters? Agentic engineering is changing how products are built. This role defines how: AI systems reason in real time Voice and chat agents operate under latency constraints Financial workflows become autonomous yet safe Multiple AI agents collaborate to produce deterministic, high-quality outcomes You will lead the engineering effort that transforms AI from an assistant into a production-grade system embedded deeply into customer experiences. We value in-person time for planning, problem-solving, and connection. Team members in this role must live within commuting distance of our Palo Alto or San Francisco office hub and this is an -site role. Compensation: Base Salary is expected to be between $200,000 - $240,000, plus performance bonus and equity options Exact compensation may vary based on skills and location. The base salary range represents the minimum and maximum of the salary range for this position based at our Palo Alto headquarters. The actual base salary offered for this position will depend on numerous factors, including individual proficiency, anticipated performance, and the location of the selected candidate. Our base salary is just one component of out competitive total rewards package, which also includes equity awards (a new hire grant), competitive health and wellness benefits. What We Offer 100% paid health, dental & vision care 401(k) match & financial wellness perks Discretionary PTO + paid parental leave Mental health, wellness & family benefits A mission-driven team shaping the future of banking At Interface.ai, we are committed to providing an inclusive and welcoming environment for all employees and applicants. We celebrate diversity and believe it is critical to our success as a company. We do not discriminate on the basis of race, color, religion, national origin, age, sex, gender identity, gender expression, sexual orientation, marital status, veteran status, disability status, or any other legally protected status. All employment decisions at Interface.ai are based on business needs, job requirements, and individual qualifications. We strive to create a culture that values and respects each person's unique perspective and contributions. We encourage all qualified individuals to apply for employment opportunities with Interface.ai and are committed to ensuring that our hiring process is inclusive and accessible.