Senior / Staff Full-Stack Engineer (Node.js + AWS)

🏢 Summary: End-to-end Infrastructure Engineer role owning AWS architecture for a distributed, event-driven system that processes payments and documents with strict correctness guarantees. You will design, operate, and automate cloud infrastructure, CI/CD, observability, and data systems to ensure deterministic state, reliability, and zero-downtime deployments. The role combines infrastructure, backend awareness, and production ownership in a high-autonomy environment. 🗂️ Requirements: 6+ years building and operating production infrastructure, Deep operational expertise in AWS services, Strong Infrastructure as Code discipline (no manual console changes), Experience designing and running event-driven architectures, Strong knowledge of distributed systems concepts (ordering, idempotency, retries, recovery), Hands-on experience with PostgreSQL, Lambda, SQS, Redis, S3, Experience building and maintaining CI/CD pipelines, Strong focus on observability, monitoring, and alerting, Experience enforcing IAM least-privilege and managing cloud security, Ability to manage multi-environment infrastructure (dev, staging, prod) with parity 📃 Skills: AWS, Lambda, SQS, S3, Redis, PostgreSQL, CDK, SAM, CloudFormation, CI/CD, IAM, TypeScript, Node.js, React, Networking, Observability, Logging, Tracing 🏢 Description: About Blue Language Labs Blue is building the trust layer the AI economy has been waiting for — a protocol for structured, verifiable, multi-party agreements that execute deterministically, leave an audit trail, and work across any system. Think smart contracts, minus the blockchain overhead. Our products are already being built and tested with real integrations: PayNotes — Programmable payments with conditional capture, milestone releases, refunds, vouchers, and partner settlement. MyOS — SaaS orchestration layer for merchants and agents. Cross-platform trust, without writing a line of Blue Language yourself. The System You’ll Own MyOS processes documents, payments, and agent interactions through a distributed, event-driven pipeline where correctness isn’t optional. State must be deterministic, ordering must be exact, and failure must be recoverable without data loss or partial writes. A bad deployment here doesn’t just cause downtime — it can silently break processing guarantees across active sessions. Understanding why that matters, and building infrastructure that prevents it, is the job. The Role You will own features end-to-end — from the React component a merchant clicks to the Lambda function that settles their transaction to the AWS infrastructure that keeps it all standing. No handoffs between "front" and "back". No waiting for someone else to unblock you. This is a high-trust, high-autonomy role. You'll work directly with the founding team, your decisions will ship to production fast, and yes — you'll be on the hook when something breaks. What You Bring Deep AWS expertise across compute, messaging, storage, networking, and observability — not just familiarity, but operational instinct built from running things in production Strong IaC discipline — CDK, SAM, or CloudFormation; you version everything, you don’t click in consoles Understanding of distributed systems fundamentals: ordering guarantees, idempotency, at-least-once delivery, outbox patterns, partial failure recovery Experience operating event-driven architectures under load — you know what failure looks like before it becomes an incident Enough application-layer literacy to read TypeScript/Node.js code and understand what a service is doing, not just that it’s running Strong opinions about observability — structured logging, distributed tracing, dashboards built for on-call humans at mam What you get? Competitive B2B compensation based on experience Equity — own a piece of what you build Fully remote work in an async-first environment Direct collaboration with the founding team High autonomy and fast decision-making Small team, outsized impact Work on technology that is genuinely novel End-to-end ownership across product, systems, and production Protocols don’t get built by committees. They get built by small teams who understood the problem before anyone else did. What You'll Do Own all AWS infrastructure end-to-end — architecture, cost, security, reliability, and compliance. No infrastructure team above you. Design and maintain CI/CD pipelines that let engineers ship confidently and fast — zero manual steps from commit to production Build monitoring and alerting that surfaces real problems early: queue depth, processing failures, latency spikes, delivery anomalies — dashboards that tell you what’s actually wrong Manage PostgreSQL at scale — configuration, connection pooling, migration strategy, performance, backup and restore Keep real-time and async processing components healthy across Lambda, SQS, Redis, S3, and the services that connect them Enforce IAM least-privilege across the system — service-to-service trust, secrets management, network isolation Manage environments (dev / staging / prod) with infrastructure parity and clean promotion paths Own cost visibility and optimization across a growing AWS footprint Use modern AI tooling to accelerate infrastructure work and experimentation Requirements We’re not looking for someone to manage servers. We’re looking for an engineer who looks at a distributed, event-driven system and immediately sees the failure modes, the ordering edge cases, and the places where a misconfigured queue will silently corrupt state. Someone who automates everything, documents why, and gets angry when something requires a manual step. 6+ years building and running production infrastructure. Deep AWS knowledge and strong operational instincts. Infrastructure as Code only — no manual steps, no console dependency. Strong distributed systems thinking: ordering, retries, idempotency, recovery. Experience with PostgreSQL, Lambda, SQS, Redis, S3, and CI/CD. Obsessed with reliability, security, visibility, and automation. Comfortable owning critical infrastructure end to end. A process that is practical, clear, and respectful of your time We keep the sequence focused so both sides can understand fit, technical quality, and the shape of the work. Introductory conversation - Up to 60 minutes - A practical conversation about your background, the kind of work you want to do next, and the context behind the role. Take-home assignment - No live coding - We prefer to evaluate technical ability through a realistic take-home task that gives you time to think and show the quality of your approach. Technical interview - Up to 90 minutes - A deeper discussion with a technical leader or senior team member about your experience, engineering judgment, and approach to the assignment. Final review - Clear feedback and a timely decision - We gather feedback, review the process carefully, and aim to communicate clearly throughout.

🏢 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: 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: B2B full-stack product engineering cooperation with a strong frontend focus, delivering user-facing hospitality software features from discovery and design through production release. The role combines VueJS-based frontend craft, daily PHP/Laravel backend work, product judgment, UX quality, and AI-augmented development in a remote-first model. 🗂️ Requirements: Strong commercial experience with TypeScript, JavaScript, VueJS, Tailwind, and Pinia, Experience with component architecture, state management, and performance, Documented backend engineering experience with PHP and Laravel, Knowledge of design patterns, APIs, caching, database query optimization, microservices, and message queues, Ability to deliver frontend and backend features end-to-end, Communicative Polish and English 📃 Skills: TypeScript, JavaScript, VueJS, Tailwind, Pinia, PHP, Laravel, Node.js, REST, Docker, GitLab, MySQL, MariaDB, MongoDB, Redis, Microservices, Kubernetes, Claude, Cursor 🏢 Description: The role This is a full-stack product engineering cooperation with a strong frontend focus. You take responsibility for technical initiatives end-to-end: from technical discovery and solution design, through implementation and testing, to release and production readiness. The Product Manager steers direction and owns the what and why. You own the how and the technical solution. Your technical home is the frontend: user journeys, component architecture, interaction design, and UX quality. You also work across the backend when practical—for example, when connecting APIs, implementing business logic, or building integrations. What you'll actually do • Deliver user-facing features end-to-end: design, build, test, and ship both the frontend and backend. • Partner with the Product Manager on technical discovery to validate feasibility, identify constraints, and shape the technical approach before scope is locked. • Own end-to-end quality and care whether the experience works in production, not only whether it passed review. • Use AI-augmented development: Claude Code is a daily driver, with MCP servers, custom agents, and internal tooling as part of the workflow. • Collaborate closely with Product Managers and backend engineers; you own the how, while the PM owns the what and why. • Maintain UX coherence by noticing recurring issues, raising them, and leaving the product better than you found it. Tech stack • Full-stack • TypeScript • JavaScript • VueJS • Node.js • Claude Code • MCP servers • AI agents • REST API • Docker • GitLab CI/CD • PHP • Laravel • MySQL / MariaDB • MongoDB • Redis • Microservices • Kubernetes What we're looking for Technical expectations: • Strong commercial experience with TypeScript, JavaScript, VueJS, Tailwind, and Pinia, including component architecture, state management, and performance. • UX sensibility: you notice problems before users complain and care about interaction quality. • Documented PHP and Laravel backend engineering experience. You understand design patterns, APIs, caching, database query optimization, microservices, and message queues. Backend development is a daily task in this full-stack role. • Hands-on experience with Claude Code, Cursor, or equivalent AI tooling is a strong plus, including generating backend integrations with AI and understanding skills, spec-driven development, and feedback loops. • Communicative Polish and English for close collaboration with PMs, QA, and software engineers. You'll enjoy collaborating with us if • You have shipped user-facing features used by real people and understand what broke and why. • You notice UI details that most engineers scroll past. • You are curious about the business reason behind a feature before building it. • You naturally take responsibility for a feature from the PM conversation through to production. • You use AI tools to move beyond the frontend boundary into full-stack work when needed. • You care about slow connections, keyboard use, and screen sizes nobody designed for. • You can assess whether a feature is worth building without needing to make the final product decision. Bonus points • You have a side project that you built, shipped, and perhaps use yourself. • You use AI tools on your own account, not only when they are provided as part of a project. • You have worked with or contributed to a design system or component library. • You have built Node.js services or backend integrations beyond the occasional CRUD endpoint. Probably not for you if • Your definition of done is a Figma-accurate implementation regardless of how it works for users. • You consider backend someone else's problem and maintain that as a firm boundary. • Your hands-on AI experience is mostly autocomplete and the occasional PR summary. Contract terms • B2B cooperation. • Monthly compensation: 15,000–25,000 PLN net, depending on experience and agreed scope of services. • Remote-first collaboration model. • International technology and product projects. • Flexible project collaboration setup. • Planned service breaks aligned with contract terms. • Opportunity to collaborate with experienced product and technology teams. • Opportunity to access selected knowledge-sharing initiatives. Recruitment process • Introductory call with the recruiter, up to 45 minutes, covering your background, what you are looking for, and mutual fit. • Technical interview with the Team Leader, Tech Lead, and Product Manager, up to 90 minutes. It includes technical questions and discussion of frontend architecture, full-stack delivery, product ownership, and practical AI use. The focus is on judgment and initiative rather than keyword recall. • Time-boxed technical task reflecting the type of services involved, reviewed together in a follow-up call. The focus is on your process, UX decisions, and how you handle work beyond the frontend.

🏢 Summary: End-to-end software engineering role focused on building and shipping high-quality product features across frontend and backend in a fast-moving, autonomous team. The position emphasizes pixel-perfect UI/UX, strong architectural thinking, and full ownership from design to deployment. Engineers operate with high trust and direct impact on a learning and research-focused product. 🗂️ Requirements: Expert-level software engineering experience, Strong proficiency in TypeScript, Experience with SvelteKit for frontend development, Experience with Node.js for backend development, Experience with Fastify, Experience with PostgreSQL, Experience with DDD patterns, Experience with CQRS patterns, Experience with Playwright for testing, Ability to build pixel-perfect UI implementations, Ability to design and ship end-to-end features across frontend and backend, Experience working with queues, Basic proficiency in Python for ML components 📃 Skills: TypeScript, SvelteKit, Tailwind, DaisyUI, Playwright, Node.js, Fastify, PostgreSQL, Python, DDD, CQRS, Queues 🏢 Description: ABOUT THE ROLE We're looking for an expert software engineer with an exceptional eye for UI/UX to join a small, high-trust engineering team. You'll own features end-to-end — from pixel-perfect frontend work to shipping backend functionality when needed. This is not a siloed role. You'll move fast, make real decisions, and have direct impact on a product used by people who care deeply about learning and research. We don't have managers. We have engineers who own their work. TECH STACK The stack is heavily TypeScript. On the frontend: SvelteKit, Tailwind, DaisyUI, and Playwright, with DDD and CQRS patterns. On the backend: Node.js, Fastify, PostgreSQL, and queues. ML components are in Python. The stack is pragmatic, not dogmatic — tools may shift as the product evolves. WHAT WE LOOK FOR Elite communication You set accurate expectations and live up to them. No surprises, no ambiguity about status or blockers. Deep resilience Bugs, crises, tough reviews — you have a large buffer before stress impacts your output. You don't crack under pressure. No ego We're here to build something great, not to manage insecurities. The best idea wins, regardless of who had it. Product mastery You understand the engineering principles behind the best software ever made — and care deeply about the difference between good and great. Independent and obsessive by nature You go deep on everything you touch. You're a lifelong learner who can't help but care about quality. Being an ex-founder is a bonus. ENGINEERING CULTURE Optional code reviews We trust you. Merge when you're ready. Ask for a second pair of eyes when you want one. Radical autonomy We don't second-guess your decisions. You own the call. High-bandwidth collaboration Constant communication means everyone has context without formal gates or status meetings. Direct feedback Code reviews are blunt, concise, and respectful. We say what we mean. Ruthless efficiency We aggressively adopt any tool — AI included — that increases speed and leverage. Limited frontend test coverage Supplemented by strong architecture and top talent, not bureaucratic QA processes. RECRUITMENT PROCESS Recruiter screening — a short intro call to align on basics. 1-on-1 with the engineering lead — a conversation about how you think and work. Technical challenge (~4 hours) — use AI, Google, or any resource you need. We care about the result, not the method. One-month paid contract — with the possibility to extend indefinitely. Honest, frequent feedback throughout so you always know where you stand. COMPENSATION & BENEFITS Salary $100,000 – $150,000 depending on experience. Equity and profit share Core team members receive both equity and profit share as part of the compensation package. Unlimited PTO Use your own judgement — we won't count days. Steep learning curve You'll grow faster here than almost anywhere else — by design, not accident. Real ownership No managers capping your authority. You own your work end-to-end, with the full trust of the team behind you.

🏢 Summary: Senior full-stack engineer role owning a high-scale real-time product from PostgreSQL through the browser. The position covers concurrent transactional systems, Redis, WebSockets, payment workflows, and production LLM features, with direct architectural ownership. 🗂️ Requirements: Proven ownership of a system scaled to hundreds of thousands or millions of users, Deep PostgreSQL experience with transactions, locking, constraints and performance under concurrent load, Production Redis experience for caching, pub/sub and distributed locking, Strong TypeScript/Node or Python experience with a React-class frontend, Proven WebSocket and real-time state synchronization experience at scale, Payment-provider experience with subscriptions, refunds and retry-safe webhooks, At least one LLM feature shipped to external users, Experience owning systems with financial or operational consequences, Architecture decision-making ownership, Strong structured problem-solving and tradeoff reasoning, Minimum 4 hours of daily overlap with US Eastern time 📃 Skills: PostgreSQL, Redis, TypeScript, Node, Python, React, WebSockets, Stripe, LLMs 🏢 Description: About the Project The product runs real-time, multiplayer-style logic for thousands of users acting within the same few seconds, backed by a transactional data layer where locking and constraints must be correct. It handles live payments, subscriptions, and webhook-driven state changes where bugs can cause financial loss. LLM features are already shipped to real external users. Responsibilities • Own the full path from database to browser, including transaction design, locking behavior, and performance under concurrent PostgreSQL load. • Run Redis in production for caching, pub/sub, and distributed locks. • Build and maintain WebSocket-based real-time state synchronization for large numbers of concurrently active users. • Own payment-provider integrations end to end, including subscriptions, refunds, and retry-safe webhook handling. • Ship LLM-powered features to production, evaluate real-world behavior, and iterate based on external user impact. • Make architecture decisions directly. • Use LLMs in the development workflow to move faster without cutting corners. Qualifications • Strong, structured thinking and problem-solving, with the ability to reason clearly about tradeoffs under pressure. • Track record of building a system that scaled to hundreds of thousands or millions of users. • Deep hands-on PostgreSQL experience: transactions, locking, constraint design, and performance under load. • Production experience with Redis for caching, pub/sub, and locking. • Strong command of TypeScript/Node or Python, paired with a React-class front end. • Proven experience with WebSockets and real-time state synchronization at scale. • Hands-on experience with a payment provider such as Stripe, covering subscriptions, refunds, and retry-safe webhooks. • At least one shipped LLM feature used by real external users, not an internal prototype or demo. • Personal ownership of a system where a bug carried real financial or operational consequences. • History of making architecture decisions rather than executing someone else's. • Minimum 4 hours of daily overlap with US Eastern time. Recruitment Process • Initial screening to confirm technical depth and availability. • Technical assessment set by the hiring team. • Interview with the CTO. • Offer and onboarding.

🏢 Summary: Senior AI-native full-stack engineer role focused on building and owning production-grade agentic systems end-to-end, from architecture to deployment and on-call. The position involves developing multi-agent workflows, RAG pipelines, and AI infrastructure, as well as delivering client-facing B2B solutions on top of an internal agent platform. Strong ownership, hands-on LLM production experience, and full-stack execution across frontend, backend, and cloud infrastructure are required. 🗂️ Requirements: 5+ years of production software engineering experience, 1-2+ years building and operating LLM systems in production, Experience deploying agentic systems with real users, Strong full-stack development experience, Hands-on experience with LLM APIs, RAG, prompt engineering, Experience with at least one agentic framework or custom orchestration, Ability to design, ship, and maintain systems end-to-end, Experience with cloud infrastructure and production deployments, Strong written English 📃 Skills: TypeScript, React, Node.js, Python, PostgreSQL, AWS, Anthropic, OpenAI, LangGraph, CrewAI, RAG, LLM, APIs, SQL, VectorDB 🏢 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, not just in a notebook. 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've also done to ourselves what we build for others: restructured how we work around AI tools, agent-first architectures, and a delivery model that doesn't need a Jira layer between thinking and shipping. This isn't theory — it's how we operate every day. Who we're looking for A senior engineer who owns outcomes, not tasks. This isn't a role for someone who's shipped "an LLM demo at a hackathon." We need someone who has already put agentic systems into production — with real users, real edge cases, real 2am Slack messages when something goes sideways. If you need a PM to translate the problem, a Jira board with three rounds of grooming, and acceptance criteria to tell you what "done" means — this isn't for you, and that's fine. If instead you read a Slack message like "accountants are losing 2 hours a day reconciling this" and your brain immediately jumps to "okay, what does the user actually need, what's the simplest thing that works, and how do we ship it" — keep reading. You'll own problems end-to-end. Frontend, backend, the agent layer, the deploy, the follow-up when a customer hits something weird. You decide what to build, you build it, you ship it, you watch what happens. And you get that this actually matters. On the other end of every feature there's an accountant closing books at 9pm, a firm owner trying to keep their business running. It's not just code. What "AI-native" actually means here Not "I've used ChatGPT." We mean: Claude Code / Cursor / Codex is your IDE , not a plugin you switch on when you feel like it. You know when "accept all" is safe and when it absolutely isn't. You have strong opinions on agent orchestration — when to reach for LangGraph/CrewAI/Agno vs. when to write 50 lines of plain Python that work better. You understand production reality of LLM systems — guardrails, evals, observability, retry logic, cost control, what to do when a model is non-deterministic in a way that breaks your contract with the user. You can tell when a model is the wrong tool and reach for code instead. For you, AI is a tool — not the point. What you'll actually own Agentic systems in production — multi-step workflows, RAG pipelines, agent orchestration. From architecture decision to deployment to the 3am on-call when something drifts. The AgentX platform itself — the primitives, the orchestration layer, the evals, the deployment story. You're building the thing that makes every client engagement faster and more reliable than the last. Full-stack client solutions on top of AgentX — TypeScript/React on the frontend, Python on the backend, integrated with LLM providers (Anthropic, OpenAI, others as they come). Infrastructure that holds up — Postgres, AWS, vector stores, ingestion pipelines, the unsexy layer that makes everything else possible. Quality standards for AI systems — you help us define what "good" looks like. Evals, guardrails, failure modes. Because "mostly right but wrong in scary ways" is not a feature. Our stack TypeScript, React, Node.js, Python, PostgreSQL, AWS, Anthropic + OpenAI APIs, agentic frameworks. You don't need every box ticked — you need to be the kind of specialist who picks up unfamiliar pieces quickly and confidently. What we expect (must-haves) 5+ years shipping production software , at least 1-2 of them with real LLM systems in production — not side projects, not demos Strong full-stack background — you're comfortable owning from frontend to infra, even if your center of gravity is one side AI-native coding workflow — Claude Code, Cursor, Codex, whatever — as your daily driver Hands-on with LLM APIs, RAG, prompt engineering, and at least one agentic framework (or you've built your own orchestration and have opinions on why) Strong written English — you'll communicate with clients, partners, and async teammates Ability to run a project from discovery to delivery with minimal supervision — we'll align on outcomes, you'll figure out how Nice-to-have Experience building B2B SaaS for non-technical users (SMBs, professional services) Voice agents, real-time systems (LiveKit or similar) Accounting / fintech / regulated domain exposure How we work Fast pace, but Monday to Friday. Weekends are yours. We don't do crunch, we don't do fake urgency, we don't do meetings that could've been a message. We'd rather ship steadily for years than sprint for six months and lose you. Direct line to the founder. Direct line to clients. No process layer between you and the work. Small team, real decisions, real ownership. The honest pitch Real ownership of real product areas — not a seat on a feature factory Frontier work — you're building both the platform that makes production agents work and the client systems running on top of it Compensation that reflects seniority — 14 000 – 25 000 PLN netto + VAT (B2B), with room above for someone exceptional Fully paid AI stack — Claude Max, Cursor, whatever you need to work at full speed Remote-first , flexible hours, Poland-based No filler meetings, no Jira bloat — we measure shipped systems in production, not hours logged Push back on the founder when he's wrong. He will be, regularly. 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: Backend engineering role focused on building scalable Python services and APIs for an AI platform used by enterprise customers. The position involves developing production backend systems, integrating AI components, and improving reliability in a collaborative engineering environment. Offers modern AI tooling, cloud-native development exposure, and growth opportunities within an AI-focused product team. 🗂️ Requirements: 2–5 years of backend application development experience, Python, REST APIs, Backend services, SQL, PostgreSQL, Asynchronous programming, Background job processing, AWS, Azure, GCP, Testing, Version control, AI development tools, English B2 📃 Skills: Python, FastAPI, Django, PostgreSQL, SQL, AWS, Azure, GCP, Docker, Redis, RabbitMQ, Kafka, TypeScript, REST, Git, CI/CD, ChatGPT, Copilot, Codex, Claude 🏢 Description: About Us Many companies want to use AI agents, but these agents often struggle with real business tasks. We solve this problem by building a platform that helps AI understand business rules, workflows, and processes. This enables AI to make better decisions and provide accurate, reliable, and trustworthy results. Our technology is used by leading companies across multiple industries to automate up to 85% of customer cases, reduce handling time by 20–25%, and complete tasks that previously took hours in just seconds. We work with leading technology partners and have been recognized for our innovative approach. Our mission is to help people everywhere get better answers through AI. About the Role We are looking for a Mid Backend Engineer to help build scalable backend services that power our AI platform. You'll work closely with experienced backend engineers, frontend developers, product managers, and platform engineers to develop new features, improve existing systems, and deliver reliable production software. This is a great opportunity to work on modern AI infrastructure while growing your technical skills in a collaborative engineering environment. Responsibilities - Build and maintain backend services, APIs, and background processing systems. - Develop scalable application logic using Python. - Collaborate with product managers and engineers to deliver new product features. - Integrate backend services with databases, external APIs, and AI components. - Monitor, troubleshoot, and improve production services. - Write clean, maintainable, and well-tested code. - Participate in code reviews and engineering discussions. - Improve development workflows using AI tools and automation. - Continuously learn from production feedback and contribute to improving system reliability and performance. Requirements - 2–5 years of experience building production backend applications. - Good knowledge of Python. - Experience building REST APIs and backend services. - Understanding of relational databases (PostgreSQL or similar) and SQL. - Familiarity with asynchronous programming and background job processing. - Basic understanding of cloud platforms such as AWS, Azure, or GCP. - Understanding of software engineering best practices, testing, and version control. - Good communication skills and willingness to collaborate across engineering and product teams. - Experience using AI development tools such as GitHub Copilot, Claude Code, ChatGPT, or similar. - English at B2 level or higher. Nice to Have - Experience with FastAPI, Django, or similar Python frameworks. - Experience working with Docker and CI/CD pipelines. - Familiarity with Redis, RabbitMQ, Kafka, or similar messaging technologies. - Experience building AI-powered applications or integrating LLM APIs. - Basic knowledge of TypeScript or frontend development. - Interest in distributed systems and cloud-native architectures. What We Offer - 20,000–24,000 PLN B2B (depending on experience). - Company stock options. - MacBook Pro. - Modern technology stack with opportunities to contribute to open-source projects. - Access to advanced AI development tools, including GitHub Copilot, Claude Code, OpenAI Codex, TypingMind, and MCP Servers. - The opportunity to work on production AI systems used by enterprise customers. - A collaborative engineering culture focused on learning, ownership, and continuous improvement. - Career growth alongside experienced engineers in a fast-growing AI company. Our Culture and Values - Quality - We build reliable software with attention to detail and long-term maintainability. - Momentum - We move quickly, learn continuously, and improve through iteration. - Accountability - We take responsibility for our work and communicate openly. - Hard Work - We solve ambitious problems together and support each other along the way. - Learning Agility - We stay curious, embrace feedback, and continuously develop our skills. - Adapt and Thrive - We welcome change and see challenges as opportunities to improve. - Win Together - We collaborate, share knowledge, and succeed as one team.

🏢 Summary: Senior or Staff Backend Engineer role focused on architecting and scaling AI-native backend services for a modern accounting platform. The position involves designing distributed systems, building secure and high-performance APIs, and establishing engineering standards to support rapid, reliable product delivery. You will work closely with Product, AI, and Operations teams to build scalable data pipelines and incident response infrastructure. 🗂️ Requirements: 5–10+ years of backend engineering experience, Proven experience designing and operating production backend systems at scale, Strong expertise in API design and data modelling, Deep understanding of distributed systems and architectural trade-offs, Hands-on experience with AWS or GCP in production environments, Practical experience with CI/CD pipelines and automated testing, Experience building and maintaining observability and on-call practices 📃 Skills: TypeScript, Node.js, React, AWS, GCP, Terraform, PostgreSQL, OpenAI, Azure, CI/CD, APIs, DistributedSystems, DataModelling, Observability 🏢 Description: ABOUT THE COMPANY We're an applied AI company building an AI-native alternative to legacy accounting software — a market worth tens of billions in annual recurring revenue. Our mission is to help entrepreneurs focus on what matters in their business and life, and to help their accountants become more strategic. We've raised $20M from a group of top-tier investors and have grown ARR 60% month-on-month since our public launch. We now serve thousands of businesses and are expanding our product to serve accountants directly — creating a two-sided platform where both business owners and their accountants use and recommend us. We're at an early but proven stage, moving fast, and building a world-class engineering team in Wrocław to match our ambition. ABOUT THE ROLE We're looking for a Senior or Staff Backend Engineer to own and evolve our backend services as we scale. This is a broad, high-impact role — you'll architect new features, build the systems that underpin our core product, and set the engineering standards that shape how the whole team works. The focus is on building a modern, AI-native developer experience. That means working closely with Product, AI, and Operations teams to design agentic systems, distributed data pipelines, and scalable incident response infrastructure — and doing it in a way that lets the team ship with confidence multiple times a day. WHAT YOU'LL WORK ON Architecture and feature design Partner with Product, AI, and Operations teams to architect new features and complex agentic systems. Make clear architectural trade-offs that balance platform, product, and business goals. Backend services and APIs Build and maintain the backend services and APIs that power the core product. Ensure systems are secure, well-tested, and high performance. Distributed systems Design and implement distributed services to orchestrate data pipelines, automate investigations, and enable incident response at scale. Operational excellence Own operational best practices so the team can ship multiple times a day with confidence. Healthy on-call culture and strong observability are part of what you'll build and maintain. Engineering standards Set the bar for writing, communication, and system design across the team. Your influence will shape how a modern AI-native product is built. WHAT WE LOOK FOR 5–10+ years of backend engineering experience A strong track record designing, building, and operating production backend systems at scale. Deep backend fundamentals Expertise in API design, data modelling, and reasoning about distributed systems trade-offs. You understand the nuances, not just the patterns. AWS or GCP hands-on experience Solid understanding of how infrastructure decisions impact application reliability and performance. You've run things in production, not just designed them. CI/CD in practice Practical experience with testing and deployment strategies in high-frequency shipping environments. Observability and on-call maturity A solid grasp of what good observability looks like and how to build healthy on-call practices that don't burn people out. Bonus Experience at an early-stage or scaling startup. Exposure to modern AI and ML systems. Experience shipping product without a dedicated product manager. TECH STACK TypeScript, React, Node.js, AWS, Terraform, PostgreSQL, OpenAI, Azure AI. The team uses GitHub, Slack, Linear, Figma, and Notion day to day. THE TEAM Small, senior, and in-person. The office is in central Wrocław, next to the main train station. The expectation is 4–5 days a week in the office — this is a deliberate choice, not a compromise. Relocation support is available for the right candidate. COMPENSATION & BENEFITS Salary $130,000 – $190,000 USD depending on experience, plus competitive equity. Wellness and commute stipend $100 per month. Hardware Premium hardware provided — MacBook Pro and AirPods. Food Daily in-office lunch and dinner. Time off 20 PTO days plus 9 US public holidays. Relocation Support available for candidates relocating to Wrocław.