Technical Project Manager

🏢 Summary: Platform / DevOps Engineer role focused on designing and operating a multi-tenant, real-time conversational AI infrastructure across public and private clouds. The position owns Kubernetes-based production environments, CI/CD, observability, inference routing, and cost optimization with strict latency and compliance requirements. The engineer shapes scalable, reliable infrastructure powering enterprise-grade AI deployments. 🗂️ Requirements: Significant production experience with Kubernetes at scale, Experience with multi-tenant SaaS architecture and isolation strategies, Hands-on experience in public and private cloud environments, Strong database expertise including replication, indexing, partitioning, tuning, Proficiency in Infrastructure as Code, Deep understanding of networking including ingress, mTLS, service mesh, DNS, Experience building and maintaining CI/CD pipelines, Experience implementing observability and monitoring systems, Experience with compliance, secrets management, and PII handling, Fluent English (B2) and Polish (C1) 📃 Skills: Kubernetes, Docker, CI/CD, Terraform, Networking, mTLS, DNS, ServiceMesh, Databases, SQL, Replication, Indexing, Partitioning, Monitoring, Observability, Cloud, SIP, WebRTC, RTP, AI, ModelAPIs 🏢 Description: About Lekta AI Founded in 2016 in Kraków, Poland , Lekta AI is a technological company working with major European banking , insurance , and telco enterprises . The company was set up with an ambitious goal of providing the best customer service in the world . Lekta stands out from the crowd of conversational AI companies because we combine technological expertise with domain-specific knowledge from contact center industry veterans . Through the use of our proprietary conversational neurosymbolic engine and backend integrations , our systems are intent- and context-aware , handling over 1.5 million conversations every month . Today, with offices in Poland and Spain , Lekta is rapidly expanding its business division to scale operations internationally . About the role Lekta is hiring a Platform / DevOps Engineer to own the infrastructure that carries our platform end-to-end — runtime, IDE, and the layers beneath . You'll work across both public cloud and private cloud deployments , because the customers we serve span both. Infrastructure decisions in this domain land directly in product quality: sub-second latency , multi-tenant isolation , deterministic compliance , and inference cost at scale all live in your remit. The systems you design now will shape how Lekta scales for years to come . We are building the next generation of conversational AI — a platform where the creator's experience is itself AI-native . Think of what Lovable did for app-building, applied to conversational agents: a visual IDE , a copilot that helps the user shape, refine and evolve the agent, and a runtime engineered to deploy what gets built into enterprise production . What makes the engineering genuinely hard is the combination our agents have to deliver simultaneously: fluent (natural language, real conversation), fast (sub-second on live voice channels), and reliable (predictable behaviour under real customer pressure, every time). Most stacks force a choice between two of those at the cost of the third. We don't , and that constraint shapes almost every engineering problem we work on. AI is a power tool , and we treat it like one. Lekta engineers are encouraged — and equipped — to use AI deeply across their work: Claude Code , model APIs , copilot tooling . We invest in the accounts, tooling, and time it takes to get fluent with them. We don't measure people on lines committed ; we measure on what gets delivered and how well it holds up in production . We are not an agentic-workflow company . AI generates; the engineer directs and reviews. Every change going out under your name has been read, understood, and signed off by you . Responsibilities Design, run and evolve Lekta's multi-tenant production infrastructure on Kubernetes across public and private cloud environments Own the infrastructure for real-time conversational channels , where latency is part of the product spec Build the routing, fallback, and reliability layer for inference workloads across multiple model providers Run cost engineering for the platform — per-tenant attribution , budgets , and optimisation of inference and infrastructure spend Establish observability that lets on-call engineers reason about agent behaviour , not just request timing Own the CI/CD pipeline that protects production deploys, with quality and regression gates Establish the compliance baseline for regulated enterprise customers — secrets , PII handling , audit trails Qualities Significant production experience running Kubernetes at meaningful scale Multi-tenant SaaS architecture background, with a clear view on isolation and pooling trade-offs Hands-on experience operating across both public and private cloud environments Strong database skills — replication, indexing, partitioning, tuning IaC fluency and configuration-level networking depth ( ingress, mTLS, service mesh, DNS ) — debugged, not just read about Articulated view on when to use managed services and when to self-host , grounded in both Track record of shipping production work with AI in your daily loop , and reviewing what it produces Real-time audio infrastructure ( SIP / WebRTC / RTP ), inference cost optimisation , or banking / fintech compliance is a plus Fluent in English (B2) and Polish (C1) ; other languages are a plus Why join us Visible impact — your engineering decisions land in real customer experience , not in roadmap slides Real ownership — few layers between you and production, and close work with engineering leadership and founders AI-first workflow with company-paid tooling — Claude Code , model access , IDEs of your choice Flexible contract types ( B2B / Employment Contract ), work arrangements , and working hours Remote, hybrid or in-office — from a location of your choice Direct, low-bureaucracy, results-oriented culture ; no micromanagement Competitive salary , with an honest conversation about trajectory as Lekta scales

🏢 Summary: Full-Stack Product Engineer role focused on building and evolving a visual IDE for designing and deploying conversational AI agents. The position involves end-to-end ownership of features across frontend and backend, including AI copilot integration, real-time simulation, and enterprise-grade UX. The engineer will deliver production-ready solutions that balance performance, reliability, and fluent AI-driven interactions. 🗂️ Requirements: Significant production experience with React, Strong proficiency in TypeScript, Experience with modern Next.js or equivalent frameworks, Full-stack development experience across API design, data modeling, and UI, Experience with relational databases, Experience using ORMs, Ability to build and ship production-ready features end-to-end, Experience integrating AI tools or model APIs into production workflows, Fluent English (B2), Fluent Polish (C1) 📃 Skills: React, TypeScript, Next.js, JavaScript, APIs, REST, SQL, ORM, AI, LLM, Claude, HTML, CSS 🏢 Description: About Lekta AI Founded in 2016 in Kraków, Poland , Lekta AI is a technological company working with major European banking , insurance , and telco enterprises . The company was set up with an ambitious goal of providing the best customer service in the world . Lekta stands out from the crowd of conversational AI companies because we combine technological expertise with domain-specific knowledge from contact center industry veterans . Through the use of our proprietary conversational neurosymbolic engine and backend integrations , our systems are intent- and context-aware , handling over 1.5 million conversations every month . Today, with offices in Poland and Spain , Lekta is rapidly expanding its business division to scale operations internationally . About the role Lekta is hiring a Full-Stack Product Engineer to build and evolve the IDE that creators use to design conversational agents — the surface where every Lekta user actually does their work. This is product engineering at the heart of the platform : visual editing , the in-product AI copilot , real-time simulation , and the workflows that decide whether building an agent feels effortful or natural . UX quality is product quality here; the people using your work spend hours inside it every day . You will own features end-to-end across the stack , work close to product and design , and ship into a real customer feedback loop . We are building the next generation of conversational AI — a platform where the creator's experience is itself AI-native . Think of what Lovable did for app-building, applied to conversational agents: a visual IDE , a copilot that helps the user shape, refine and evolve the agent, and a runtime engineered to deploy what gets built into enterprise production . What makes the engineering genuinely hard is the combination our agents have to deliver simultaneously: fluent (natural language, real conversation), fast (sub-second on live voice channels), and reliable (predictable behaviour under real customer pressure, every time). Most stacks force a choice between two of those at the cost of the third. We don't , and that constraint shapes almost every engineering problem we work on. AI is a power tool , and we treat it like one. Lekta engineers are encouraged — and equipped — to use AI deeply across their work: Claude Code , model APIs , copilot tooling . We invest in the accounts, tooling, and time it takes to get fluent with them. We don't measure people on lines committed ; we measure on what gets delivered and how well it holds up in production . We are not an agentic-workflow company . AI generates; the engineer directs and reviews. Every change going out under your name has been read, understood, and signed off by you . Responsibilities Build and evolve the IDE that creators use to design, refine and ship conversational agents — visual editor , simulation , debugging , observability surfaces Build the in-product AI copilot — the assistant that helps users shape, refine, and evolve their agents inside the IDE Own product features end-to-end : from API and data model to UI , including sharing , collaboration , and multi-tenant workflows Deliver high UX quality at the level enterprise customers expect of a tool they spend hours in every day — typography , layout , motion , performance Integrate with the runtime layer to surface live simulation , traces , and operational signals into the IDE Work closely with product , design , and users — both on what to build next and on whether what shipped actually solved the problem Qualities Significant production experience with React and TypeScript at depth , including modern Next.js (or equivalent) patterns Strong full-stack range — comfortable moving between API design , data modelling , and UI in a single feature, owning what you ship after release Eye for UX — you notice when interactions are off, you care about typography , motion , layout , and performance , and you hold the bar even when nobody is watching Comfort with relational databases and ORMs — you can model a feature's data layer without needing a backend specialist on call Track record of shipping production work with AI in your daily loop , and reviewing what it produces Experience building visual editors , AI copilot / assistant interfaces , or developer tools is strongly preferred Fluent in English (B2) and Polish (C1) ; other languages are a plus Why join us Visible impact — your engineering decisions land in real customer experience , not in roadmap slides Real ownership — few layers between you and production, and close work with engineering leadership and founders AI-first workflow with company-paid tooling — Claude Code , model access , IDEs of your choice Flexible contract types ( B2B / Employment Contract ), work arrangements , and working hours Remote, hybrid or in-office — from a location of your choice Direct, low-bureaucracy, results-oriented culture ; no micromanagement Competitive salary , with an honest conversation about trajectory as Lekta scales

🏢 Summary: The offer is for a Software Engineer (Agent Development) role focused on building and scaling production-ready AI agents and autonomous marketing workflows. The position combines strong backend engineering with applied GenAI, emphasizing reliable, scalable systems integrated into a live marketing automation platform. The role involves working with LLM orchestration, backend services, and AI-driven integrations in a fast-paced, collaborative environment. 🗂️ Requirements: 2–4 years of software engineering experience, Strong experience in Python and scalable backend development, Understanding of building production-ready, maintainable systems, Interest in AI, GenAI, and agentic systems, Experience with backend databases such as MySQL, Redis, or DynamoDB, Ability to work in fast-paced, iterative environments, Strong problem-solving skills, Ability to collaborate with cross-functional and distributed teams 📃 Skills: Python, GenAI, LLM, MySQL, Redis, DynamoDB, APIs, CI/CD, Cloud, AI, Agents 🏢 Description: Our client helps small teams power big businesses with the must-have platform for intelligent marketing automation. Customers from over 170 countries depend on the Client’s mix of pre-built automation and integration to power personalized marketing, transactional emails, and one-to-one CRM interactions throughout the customer lifecycle. We’re looking for a Software Engineer (Agent Development) to join our client’s growing AI team and help build the next generation of autonomous AI agents powering modern marketing workflows. In this role, you’ll work at the intersection of backend engineering and applied AI, designing and scaling production-ready agentic systems used by businesses worldwide. This is not a pure research role. The focus is on strong software engineering fundamentals and building reliable, scalable AI-powered products. You’ll work across backend systems, orchestration, integrations, and AI workflows, collaborating closely with cross-functional product and engineering teams. The environment is fast-paced and highly collaborative, with a strong emphasis on ownership, rapid iteration, and building real-world AI solutions already running in production. Key takeaways: Stack: Python, AI Agents, MySQL, GenAI Salary : 20 000 - 23 000 PLN gross/month, Contract of employment (+10% annual bonus, 75% Creative Tax) Working model: Hybrid, once a week in the office Location: Krakow, ul. Konopnickiej Recruitment process: Call with MOTIFE recruiter (30 min) Technical interview, live coding (1h) Cross-functional interview (1h) Interview with Hiring Manager (45 min) | Optional Responsibilities: Design and develop production-grade AI agents and autonomous marketing workflows across the platform. Build and maintain multi-step agentic systems involving LLM orchestration, tool usage, and backend integrations. Work with LLM APIs, including prompt engineering, response handling, evaluation, and optimization of AI workflows. Create and improve evaluation frameworks, quality metrics, and monitoring processes to ensure agent reliability and performance at scale. Monitor and optimize agent behavior, latency, token usage, cost efficiency, and production stability. Develop production-quality backend services and orchestration layers primarily using Python. Contribute to backend and frontend integration points where AI agents interact with the core platform. Build and maintain APIs, service interfaces, and data flows supporting AI-driven capabilities. Collaborate closely with Product, Design, and Engineering teams to define and deliver AI-powered user experiences. Ensure code quality through testing, code reviews, and adherence to engineering best practices. Participate in on-call rotations supporting AI agent services and platform reliability. Contribute to technical documentation, architectural decisions, and AI engineering best practices. Collaborate closely with globally distributed teams, including regular overlap with US-based stakeholders. Requirements: 2–4 years of experience in software engineering, with strong backend development fundamentals. Strong hands-on experience with Python and building scalable backend services. Interest in AI, GenAI, and agentic systems, with a willingness to grow in this area professionally. Exposure to AI-related projects, LLM-based solutions, ML models, or personal AI experiments is considered a strong plus. Understanding of how to build reliable, maintainable, and production-ready systems. Ability to work in fast-paced, iterative environments and ship code quickly while maintaining engineering quality. Familiarity with modern backend and database technologies such as MySQL, Redis, or DynamoDB. Strong problem-solving skills and the ability to work across different systems and technologies. Experience with cloud environments, APIs, CI/CD practices, or observability tooling is a plus. Familiarity with AI agent frameworks, prompt engineering, or LLM workflows is nice to have, but not required. Strong communication skills and a collaborative mindset within cross-functional engineering teams. Willingness to collaborate with globally distributed teams, including regular overlap with US-based stakeholders. What we offer: Health Benefits 1. Medical Full coverage for employees and their dependents through LUX MED. Employees have access to the “Premium” package, providing enhanced coverage and greater access to care. A client pays 100% of the premium for employees and 50% for dependents. 2. Dental No additional cost for dental coverage- integrated into LUX MED medical plan. 3. Vision Reimbursement for vision expenses up to 400 PLN every 2 years. Mental Health Tools Access to TELUS Health EAP to provide support and resources in a time of need. Additional Benefits 10% annual bonus 75% Creative Tax Vacation: 26 days. Home Office Stipend: One-time $150 equivalent home office stipend to outfit their home office. Calm Subscription: Premium subscription access to Calm, the #1 app for sleep, meditation, and relaxation. Hub Perks: Receive meal and transportation benefits when traveling to the Poland Hub. Baby Swag: If you have a baby or adopt, you’ll receive a company-branded first bath bundle. Sabbatical Program: After 5 years of employment, receive a month-long paid sabbatical leave, with a sabbatical leave bonus.

🏢 Summary: Senior Lead Engineer role focused on leading architecture and delivery of high-scale enterprise systems using React, Node.js, and TypeScript, while integrating advanced AI agents into deterministic workflows. The position combines hands-on development, technical leadership, and ownership of mission-critical systems in close collaboration with AI architects. It offers high impact on production-ready AI solutions for global enterprises. 🗂️ Requirements: 10+ years of software engineering experience, Proven experience in Lead, Principal, or Expert engineering roles, Expert-level knowledge of React, Expert-level knowledge of Node.js, Expert-level knowledge of TypeScript, Experience designing and scaling enterprise systems, Experience conducting code reviews and mentoring engineers, Ability to integrate AI/LLM agents into enterprise systems, Strong problem-solving skills for complex production issues, English proficiency at minimum B2 level 📃 Skills: React, Node.js, TypeScript, JavaScript, LLM, AI, Neurosymbolic, State, Machines, Python, NX, Snowflake 🏢 Description: Position: Senior Lead Engineer (React, Node.js & AI) Location: Kraków (On-site) Salary: 35,000 – 45,000 PLN net + VAT (B2B) + 10% yearly performance bonus About the Project Our Client is an innovative software company specializing in transforming raw AI capabilities into durable, deterministic enterprise systems. Known for their elite engineering culture, they specialize in delivering high-scale, production-ready AI solutions for global Fortune 500 enterprises. As a Senior Lead Engineer, you will become the right hand to the Principal Architect. This is a high-impact, operational leadership role where you will take full accountability for core React/Node/TS interfaces and backend systems, mentor the engineering team, and seamlessly integrate cutting-edge AI agents into complex enterprise workflows. Your leadership will drive delivery, allowing the Principal Architect to focus entirely on macro-level AI strategies and frontier models. Your Role Architecture & Delivery: Designing, building, and scaling core enterprise systems and interfaces using React, Node.js, and TypeScript. Technical Leadership: Taking extreme ownership of the codebase, enforcing world-class standards, conducting code reviews, and mentoring the engineering team to help them grow into independent problem solvers. AI Integration: Collaborating closely with the AI architecture team to embed LLM agents, neurosymbolic systems, and state machines into secure, deterministic enterprise workflows. Problem Solving: Acting as the ultimate escalation point for complex technical challenges, leading the charge to unblock production when critical issues arise. Strategic Execution: Translating high-level business requirements and macro-architecture directly into flawless, high-performing code that creates durable operating leverage. Requirements Experience: 10+ years of hard-core software engineering experience, with a proven track record in Lead, Principal, or Expert roles. Tech Stack Mastery: Absolute, atomic-level expertise in React, Node.js, and TypeScript ecosystem. Extreme Ownership: A proactive mindset – you don’t wait for tasks; you identify problems, design solutions, align resources, and deliver with absolute certainty. Leadership & Mentoring: Ability to elevate the team, set uncompromising quality standards, and guide junior/mid engineers. Business DNA: Deep understanding that code serves tangible business goals (ROI) and creates long-term value, rather than just being technical art. Communication: English at minimum B2 level to collaborate effectively with an elite team and global partners. Nice to have Practical experience or strong interest in Python, NX, and Snowflake. Hands-on exposure to frontier AI/LLM models and agents. What We Offer Global Impact: The chance to build next-generation neurosymbolic systems redefining how global enterprises utilize AI. Elite Environment: Direct collaboration alongside C-level executives, visionaries, and core software architects. High-End Hardware: New Apple MacBook Pro and external monitors provided as needed. Flexible Culture: Flexible working hours within a modern, fully-equipped office setup. Premium Office Perks: Access to a modern office in Kraków featuring a playroom, bike parking, shower, free coffee, beverages, and snacks (with no dress code). Growth & Benefits: Dedicated conference budget to support your continuous professional development.

🏢 Summary: Engineering role focused on designing, building, and optimizing AI-driven microservices that power a conversational marketplace assistant. The position involves LLM orchestration, Retrieval-Augmented Generation, semantic search, and high-performance retrieval in a cloud-native environment. You will own end-to-end development of AI services across Java/Kotlin and Python ecosystems, ensuring scalability, low latency, and high availability. 🗂️ Requirements: Proficiency in Python, Proficiency in Java, Proficiency in Kotlin, Experience with LLM orchestration, Experience with Retrieval-Augmented Generation (RAG), Experience with semantic search and vector search, Experience building microservices, Experience with cloud-native architectures, Ability to design and optimize high-availability systems, English level B2 or higher 📃 Skills: Python, Java, Kotlin, Spring, ADK, LangChain, Langfuse, LLM, RAG, LoRA, PEFT, AutoGen, CrewAI, Kubernetes, Docker, Consul, GitHub, GitHubActions, VectorSearch, Embeddings 🏢 Description: About the job: Performance & Scale: Design, build, and optimize AI-driven systems that process complex natural language interactions. Delivering low-latency, high-quality responses from our AI Assistant requires high-availability and smart optimization of LLM and retrieval workloads in practice. Modern Tech Stack: Work with a world-class, cloud-native polyglot environment. Our core backend technologies include Java , Kotlin , Spring, and ADK . At the same time, our AI and orchestration layer heavily relies on Python . You will utilize Python and LangChain for complex LLM orchestration, alongside Langfuse for observability, prompt tracking, and evaluation. We leverage advanced vector search and modern ML solutions to make our assistant truly smart. True Ownership & Autonomy: We live by a "you build it, you run it" philosophy. You'll join an agile, autonomous team with full ownership of your AI microservices and data pipelines, from design to deployment; and improvements are dictated by results of our own experiments and AI evaluation metrics. Complex Challenges: From LLM orchestration and Retrieval-Augmented Generation (RAG) to semantic search optimization, you'll tackle the complex backend problems that power a conversational marketplace assistant. You will work across the Java/Kotlin and Python ecosystems, integrating advanced embedding models, prompt pipelines, and vector databases to ensure our AI deeply understands and accurately retrieves information. In our domain, we focus on delivering the core search and retrieval capabilities for the Allegro AI Assistant. We maintain a critical entry point for users looking to discover products, compare offers, and get personalized recommendations through natural conversations. Striving for relevancy and accuracy first, we are designing, implementing, and operating an extensive system combining modern microservice architecture with Large Language Models, high-performance retrievers, and vast data sources. We care about data quality, robust context building, and near real-time accuracy to best guide users through a highly dynamic marketplace via an intelligent, conversational interface. Important things for you: Flexible working hours in the hybrid model (4/1) - working hours start between 7:00 a.m. and 10:00 a.m. We also have 30 days of occasional remote work. The salary range for this position depending on the skill set is as follows (contract of employment, tax-deductible cost): PLN 14 200 - 20 200 Annual bonus based on your annual performance and company results. Our team is based in Poznań. We are looking for people who: Code in Python, Java and Kotlin ; Expect work that requires creative approach to search experience challenges, to be proud of enjoying its results together with all Allegro users; Want to create solid code, eagerly accept comments and share knowledge during code reviews; Can look for effective solutions to the requirements set by users; Want to constantly develop and update their knowledge; Know English at at least B2 level. Nice to have: You are open to diverse technologies and workflows, including dev-operational tools on one hand, and working with data on the other. Basic experience with LLM tuning (LoRA, PEFT), training and evaluation pipelines for models and/or basic frameworks for building AI Agents (Agent Development Kit, LangChain, AutoGen, CrewAI) would be great! What's in it for you: Well-located offices (with e.g. fully equipped kitchens, bicycle parking, terraces full of greenery) and excellent work tools (e.g., raised desks, ergonomic chairs, interactive conference rooms). A 16" or 14" MacBook Pro or corresponding Dell with Windows (if you don't like Macs) and all the necessary accessories. A wide selection of fringe benefits in a cafeteria plan - you choose what you like (e.g., medical, sports or lunch packages, insurance, purchase vouchers). English classes that we pay for related to the specific nature of your job. A training budget, inter-team tourism ( see more here ), hackathons, and an internal learning platform where you will find multiple trainings. An additional day off for volunteering, which you can use alone, with a team, or with a larger group of people connected by a common goal. Social events for Allegro people - Spin Kilometers, Family Day, Fat Thursday, Advent of Code, and many other occasions we enjoy. And that's just the beginning! You can read more about the benefits here . #goodtobehere means that: You will join a team you can count on - we work with top-class specialists who have knowledge- and experience-sharing in their DNA. You will love our level of autonomy in team organization, the space for continuous development, and the opportunity to try new things. You get to choose which technology solves the problem and you are responsible for what you create. You will value our Developer Experience and the full platform of tools and technologies that make creating software easier. We rely on an internal ecosystem based on self-service and widely used tools such as Kubernetes, Docker, Consul, GitHub, and GitHub Actions. Thanks to this, you can contribute to Allegro from your very first days on the job. You will be equipped with modern AI tools to automate repetitive tasks, allowing you to focus on developing new services and refining existing ones (also leveraging AI support). You will create solutions that will be used (and loved!) by your friends, family and millions of our customers. You will meet the Allegro Scale , which starts with over 1000 microservices, an open-source data bus (Hermes) with 300K+ rps, a Service Mesh with 1M+ rps, tens of petabytes of data, and production-used machine learning. You will become part of Allegro Tech - We speak at industry conferences, cooperate with tech communities, run our own blog (it's been over 10 years!), record podcasts, lead guilds, and we organize our own internal conference - the Allegro Tech Meeting. We create solutions we love (and can) to talk about! Send us your CV and… see you at Allegro!

🏢 Summary: The role focuses on designing, building, and optimizing AI-driven backend systems that power a large-scale conversational assistant with low-latency, high-availability requirements. You will work across Java/Kotlin and Python ecosystems to implement LLM orchestration, RAG pipelines, and semantic search solutions within a cloud-native microservices architecture. The position involves full ownership of AI microservices and data pipelines from design to deployment in a production-scale environment. 🗂️ Requirements: Proficiency in Python, Proficiency in Java, Proficiency in Kotlin, Experience with LLM orchestration and RAG, Experience with microservices architecture, Experience with vector search and semantic search, Experience with cloud-native environments, Ability to design and optimize high-availability, low-latency systems, English level B2 or higher 📃 Skills: Python, Java, Kotlin, Spring, ADK, LangChain, Langfuse, LLM, RAG, Kubernetes, Docker, Consul, GitHub, GitHubActions, VectorSearch, Microservices 🏢 Description: About the job: Performance & Scale: Design, build, and optimize AI-driven systems that process complex natural language interactions. Delivering low-latency, high-quality responses from our AI Assistant requires high-availability and smart optimization of LLM and retrieval workloads in practice. Modern Tech Stack: Work with a world-class, cloud-native polyglot environment. Our core backend technologies include Java , Kotlin , Spring, and ADK . At the same time, our AI and orchestration layer heavily relies on Python . You will utilize Python and LangChain for complex LLM orchestration, alongside Langfuse for observability, prompt tracking, and evaluation. We leverage advanced vector search and modern ML solutions to make our assistant truly smart. True Ownership & Autonomy: We live by a "you build it, you run it" philosophy. You'll join an agile, autonomous team with full ownership of your AI microservices and data pipelines, from design to deployment; and improvements are dictated by results of our own experiments and AI evaluation metrics. Complex Challenges: From LLM orchestration and Retrieval-Augmented Generation (RAG) to semantic search optimization, you'll tackle the complex backend problems that power a conversational marketplace assistant. You will work across the Java/Kotlin and Python ecosystems, integrating advanced embedding models, prompt pipelines, and vector databases to ensure our AI deeply understands and accurately retrieves information. In our domain, we focus on delivering the core search and retrieval capabilities for the Allegro AI Assistant. We maintain a critical entry point for users looking to discover products, compare offers, and get personalized recommendations through natural conversations. Striving for relevancy and accuracy first, we are designing, implementing, and operating an extensive system combining modern microservice architecture with Large Language Models, high-performance retrievers, and vast data sources. We care about data quality, robust context building, and near real-time accuracy to best guide users through a highly dynamic marketplace via an intelligent, conversational interface. Important things for you: Flexible working hours in the hybrid model (4/1) - working hours start between 7:00 a.m. and 10:00 a.m. We also have 30 days of occasional remote work. The salary range for this position depending on the skill set is as follows (contract of employment, tax-deductible cost): PLN 14 600 - 20 825 Annual bonus based on your annual performance and company results. Our team is based in Poznań. We are looking for people who: Code in Python, Java and Kotlin ; Expect work that requires creative approach to search experience challenges, to be proud of enjoying its results together with all Allegro users; Want to create solid code, eagerly accept comments and share knowledge during code reviews; Can look for effective solutions to the requirements set by users; Want to constantly develop and update their knowledge; Know English at at least B2 level. Nice to have: You are open to diverse technologies and workflows, including dev-operational tools on one hand, and working with data on the other. Basic experience with LLM tuning (LoRA, PEFT), training and evaluation pipelines for models and/or basic frameworks for building AI Agents (Agent Development Kit, LangChain, AutoGen, CrewAI) would be great! What's in it for you: Well-located offices (with e.g. fully equipped kitchens, bicycle parking, terraces full of greenery) and excellent work tools (e.g., raised desks, ergonomic chairs, interactive conference rooms). A 16" or 14" MacBook Pro or corresponding Dell with Windows (if you don't like Macs) and all the necessary accessories. A wide selection of fringe benefits in a cafeteria plan - you choose what you like (e.g., medical, sports or lunch packages, insurance, purchase vouchers). English classes that we pay for related to the specific nature of your job. A training budget, inter-team tourism ( see more here ), hackathons, and an internal learning platform where you will find multiple trainings. An additional day off for volunteering, which you can use alone, with a team, or with a larger group of people connected by a common goal. Social events for Allegro people - Spin Kilometers, Family Day, Fat Thursday, Advent of Code, and many other occasions we enjoy. And that's just the beginning! You can read more about the benefits here . #goodtobehere means that: You will join a team you can count on - we work with top-class specialists who have knowledge- and experience-sharing in their DNA. You will love our level of autonomy in team organization, the space for continuous development, and the opportunity to try new things. You get to choose which technology solves the problem and you are responsible for what you create. You will value our Developer Experience and the full platform of tools and technologies that make creating software easier. We rely on an internal ecosystem based on self-service and widely used tools such as Kubernetes, Docker, Consul, GitHub, and GitHub Actions. Thanks to this, you can contribute to Allegro from your very first days on the job. You will be equipped with modern AI tools to automate repetitive tasks, allowing you to focus on developing new services and refining existing ones (also leveraging AI support). You will create solutions that will be used (and loved!) by your friends, family and millions of our customers. You will meet the Allegro Scale , which starts with over 1000 microservices, an open-source data bus (Hermes) with 300K+ rps, a Service Mesh with 1M+ rps, tens of petabytes of data, and production-used machine learning. You will become part of Allegro Tech - We speak at industry conferences, cooperate with tech communities, run our own blog (it's been over 10 years!), record podcasts, lead guilds, and we organize our own internal conference - the Allegro Tech Meeting. We create solutions we love (and can) to talk about! Send us your CV and… see you at Allegro!

🏢 Summary: Lead the development of a production-grade backend powering AI features, including APIs, data pipelines, and orchestration for large-scale LLM systems. The role focuses on building reliable, secure, and scalable services handling retrieval, streaming, tool-calling, and distributed workloads on confidential data. You will own architectural decisions and ensure performance and robustness in AI-driven systems. 🗂️ Requirements: 7+ years of experience delivering production backend systems, 6+ years of experience with Python, 3+ years of experience with FastAPI, 2+ years of experience with Redis, Strong experience with PostgreSQL and SQL, Experience building and shipping LLM systems (RAG, tool-calling, agents), Experience designing async and distributed systems, Ability to architect scalable and secure backend systems 📃 Skills: Python, FastAPI, PostgreSQL, SQL, Redis, LLM, RAG, LangChain, LlamaIndex, APIs, Embeddings, VectorSearch 🏢 Description: About us comm1t is a specialist IT recruitment agency delivering top engineers across Poland and Europe 🇪🇺. We combine experienced recruiters with autonomous AI agents and an obsessive focus on quality — sourcing 24/7 across LinkedIn, GitHub, and beyond to reach engineers who aren't actively job hunting but are open to the right move. We don't flood you with CVs. We get to know each candidate's skills, values, and goals, then send only the best-matched people — and we stay close through onboarding and the first months to make sure the placement lasts. About the role You'll lead the backend that drives the AI features — the APIs, the data pipelines, and the orchestration that connects the product to the language models doing the actual work. In practice that's querying across large document sets, getting trustworthy answers out of LLMs and their tool calls, pushing results to the UI as they stream, and grinding through lengthy background jobs without the whole thing toppling over. Forget CRUD. The real difficulty is making AI systems fast and reliable on confidential data, at production scale. The architecture choices land on you early, and you'll be the one living with them. What you'll do Architect and ship the APIs and services that everything else depends on Own the AI plumbing end to end: retrieval, orchestration, tool-calling, streaming, and the evals that tell you whether the results are worth anything Make async and distributed workloads rock-solid — document ingestion, embeddings, and long jobs running on Redis Wire up integrations with what clients already use (email, document stores) and harden them for real-world traffic Put data security and isolation front and center, because clients are handing over material they can't afford to leak Who you are Seven years or more delivering production backends — though how deep you go matters more to us than the figure itself You think in failure modes, not just the happy path You've shipped genuine LLM systems (RAG, tool-calling, agents), or you can't wait to — and you've got a feel for where they fall apart You lean on AI coding tools (Claude Code, Cursor, Copilot) and get real value from them: more speed, yes, but you grasp and back every line — code you'd reject in someone else's review is code you won't merge in your own A startup that keeps changing course doesn't faze you — plans get set, then torn up and redrawn Tech stack experience Python: 6+ years FastAPI: 3+ years PostgreSQL / SQL Redis: 2+ years Nice to have RAG or vector search experience LangChain or LlamaIndex

🏢 Summary: Lead AI Software Developer role focused on architecting and scaling AI-powered applications, backend systems, and multi-agent workflows across cloud and enterprise environments. The position involves designing secure integrations, optimizing LLM-based solutions, and leading technical delivery and best practices. It combines hands-on AI development with backend architecture and technical leadership. 🗂️ Requirements: Degree in Computer Science, AI, Data Science or related field, 8+ years of software engineering experience, 5+ years of Python backend development in production, Experience building and scaling Python applications, Hands-on experience with AI Agents, RAG and MCP, Experience with AWS or Azure cloud platforms, Experience with storage systems and databases, Knowledge of containerization and Kubernetes, Experience with API integrations and enterprise system connectivity, Leadership and mentoring experience 📃 Skills: Python, AWS, Azure, Kubernetes, RAG, MCP, APIs, Cloud, Databases, Containerization, AI, LLM 🏢 Description: We are seeking an experienced Lead AI Software Developer to design and scale AI-powered applications and integrations. In this role, you will architect backend systems, lead AI agent development, and ensure secure, scalable integration across cloud platforms and enterprise systems. Key Responsibilities Design and maintain middleware, APIs, and connectors integrating AI agents with enterprise systems Architect scalable backend services and cloud-based solutions (AWS/Azure) Develop and optimize multi-agent workflows and adaptive decision logic Fine-tune prompts and LLM-based solutions for domain-specific use cases Lead code reviews, mentor developers, and define development best practices Drive complex API integrations with internal and external AI platforms (incl. MCP servers) Remove technical roadblocks and ensure timely delivery Collaborate with AI, Data, and Platform teams to optimize automation architectures Maintain technical documentation and promote continuous improvement Requirements Degree in Computer Science, AI, Data Science, or similar field 8+ years of software engineering experience, including 5+ years of Python backend development (production) Strong experience building and scaling Python applications Hands-on experience with AI technologies (AI Agents, RAG, MCP) Experience with cloud platforms (AWS or Azure), storage, databases, and AI services Knowledge of containerization and Kubernetes Experience with API integrations and enterprise system connectivity Strong leadership and mentoring experience Excellent communication skills; fluent in Polish and English (min. B2); German is a plus Willingness to travel internationally (~10%) Nice to have: Experience with LangChain, LangGraph, multi-agent systems, prompt engineering, and LLM fine-tuning. What We Offer Work in a global and innovative technology environment Direct impact on enterprise AI and automation solutions Professional development and access to training programs Hybrid work model with flexible hours (central Wroclaw office) Competitive benefits package, cafeteria system, CSR initiatives, and employee clubs

🏢 Summary: Design and optimize advanced LLM- and agentic AI-based conversational solutions for a large-scale travel Chat Assistant. The role focuses on prompt engineering, transactional AI flows, function calling integrations, and continuous architectural improvements to enhance natural language understanding and end-to-end automation. You will prototype, deploy, test, and refine LLM-driven features in collaboration with engineering teams. 🗂️ Requirements: 3+ years commercial experience in DataScience or MachineLearning, Expertise in designing and optimizing LargeLanguageModels (e.g. ChatGPT, GPT-4), Proficiency in Python, Experience with AI/NLP platforms (e.g. CognigyAI, Databricks), Hands-on performance evaluation (A/B testing, error analysis), Experience building LLM-backed transactional flows, Experience implementing function calling to backend systems or APIs, Experience with automated testing of AI solutions, Strong understanding of GenAI and agentic AI concepts, Ability to troubleshoot and optimize model behavior in conversational scenarios 📃 Skills: Python, MachineLearning, DataScience, NLP, LLM, ChatGPT, GPT-4, GenAI, AgenticAI, PromptEngineering, CognigyAI, Databricks, APIs, ABtesting, Testing, Architecture 🏢 Description: Chat Assistant is used by over 10 million travelers, it’s evolving from a traditional conversational bot into an advanced, agentic AI. It’s not just about answering FAQs - this assistant already handles end-to-end transactions like rebookings and refunds today, offering a truly seamless travel support experience. The team’s mission is to create the most intelligent, intuitive conversational experience in the travel industry via the move to Agentic AI. Your responsibilities: Craft and fine-tune advanced LLM prompts to drive high-performance conversational experiences in the Chat Assistant. Use a data-driven approach to identify limitations in current conversational models and generate effective solutions for challenges such as user engagement, contextual understanding, and content moderation. Design reusable frameworks that encapsulate innovative functionalities and can be adapted across various assistant use cases. Collaborate closely with engineering teams to align GenAI strategies with backend enhancements, contributing to architectural optimization and improved task performance. Prototype, deploy and maintain new LLM or agentic AI based strategies to support emerging features and expand the assistant’s capabilities. Continuously evolve the LHG Chat Assistant architecture with a focus on deepening the assistant’s natural language understanding and response relevance, integrating agentic AI principles to enable more adaptive, goal-oriented interactions in our redesigned system. Build LLM-backed transactional flows. Transition towards agentic AI, orchestrate hybrid solution with AI + deterministic logic. Implement and maintain function calling to backend systems or APIs. Automated testing for all components of AI solutions (prompt, flows, function calls, etc.). Our requirements: At least 3 years of commercial experience in Data Science or Machine Learning, Expertise in designing, testing, and optimizing solutions for large language models (e.g., ChatGPT, GPT-4). Proficiency in Python and at least one AI/data- platform (e.g. CognigyAI, databricks) Hands-on expertise with AI/NLP platforms and performance evaluation (A/B testing, error analysis). Solid grasp of current AI/ML research, with a focus on best practices for GenAI and emerging agentic AI concepts. Strong collaborator in agile, cross-functional teams, with excellent technical communication. Awareness of ethical AI practices, including bias mitigation and data privacy. Ability to translate complex concepts into accessible language for non-technical stakeholders. A systematic approach to identifying issues in existing setup and constructing targeted solutions, including the ability to troubleshoot and optimize model behavior under different conversational scenarios. Very good command of English language, Proactive attitude and the ability to work as a team player, The ability to think beyond the current scope of the project, Experience actively participating in a Scrum team by bringing in new solutions, Willingness to travel once per quarter, Willingness to upskill on your own initiative and deriving further insights from data, Willingness to come to our office in Gdańsk two days a week or relocate to Trójmiasto. What do we offer? An international working environment, atmosphere that stimulates development, Individual career path, Lufthansa Group membership benefits, Salary in the range of: Standard position 11 000 - 16 000 zł gross (contract of employment) Senior position 14 000 - 21 000 zł gross (contract of employment) Flexible working time and place adjusted to employee’s needs. Possibility of starting your workday between 07:00 and 11:00. Support for your passion for sports within the local activity group and co-financing Multisport cards. Private medical care for employees and their family members. Life insurance. Parking space for employees. Extra social benefits. Holiday funds. Sharing the costs of holidays for kids. Sharing the commuting costs. Modern office in Oliwa – great location and comfortable workspace. Atmosphere – small teams, high independence, real impact on the project.

🏢 Summary: Hybrid Python AI Developer role focused on building AI-powered services and automation solutions using Large Language Models and agent-based workflows. The position involves developing RAG-based bots and assistants, implementing agentic workflows, and collaborating on high-quality AI frameworks. It offers the opportunity to work on advanced LLM solutions in a dynamic, innovation-driven environment. 🗂️ Requirements: Minimum 3 years of experience in software development with Python, Practical knowledge of LangChain and LangGraph, Experience with RAG, embeddings, vector search, LLM agents, agentic workflows, tool calling, At least 1 year of hands-on experience with LLM models, RAG, and AI agents in real projects, Proficiency with Git (branch management, rebase, cherry-pick, revert, squash), Familiarity with Jira, Confluence, Bitbucket, Competent command of Polish, Communicative level of English, Legal right to work in the European Union 📃 Skills: Python, LangChain, LangGraph, RAG, LLM, Embeddings, VectorSearch, Git, Jira, Confluence, Bitbucket, Azure, React, Streamlit, Databricks, CosmosDB, Redis, Grafana 🏢 Description: Unleash the future of AI by building innovative Large Language Model solutions that redefine automation and intelligence. Warszawa-based opportunity with hybrid work model (4 days remote, 1 day in the office). As a Python AI Developer , you will be working for our client, a leading innovator in AI technology. You will contribute to developing cutting-edge services and applications supporting automation processes, leveraging advanced LLM solutions and agent-based workflows. This role offers a chance to be at the forefront of AI innovation and accelerate your career growth in a dynamic environment. Your main responsibilities: Build AI-powered services and applications in Python to support automation initiatives. Develop bots and assistants based on Large Language Models, including RAG solutions and multi-step task agents. Implement agentic workflows: define roles, manage tools, and oversee execution processes. Work with internal and new AI frameworks, ensuring high quality and alignment with best practices. Collaborate with cross-functional teams to troubleshoot, analyze issues, and optimize solutions. Maintain adherence to development standards and contribute to continuous improvement initiatives. Document system designs and participate in architectural discussions. You're ideal for this role if you have: Minimum 3 years of experience in software development, particularly with Python. Practical knowledge of LangChain and LangGraph. Experience with RAG, embeddings, vector search, LLM agents, agentic workflows, and tool calling. At least 1 year of hands-on experience with LLM models, RAG, and AI agents in real projects. Proficiency with Git, including branch management and commit operations (rebase, cherry-pick, revert, squash). Familiarity with Jira, Confluence, Bitbucket. Strong problem-solving skills and ability to work independently in a collaborative environment. It is a strong plus if you have: Knowledge of Azure AI Stack (AI Foundry, Azure OpenAI, Azure AI Search). Experience with React, Streamlit, Databricks, Cosmos DB, Redis, or Grafana. Understanding of ML fundamentals and fine-tuning LLMs. Skills in high-level system architecture design and documentation. Language Required for the role: Polish – competent command. English – communicative level. Eligibility for the role: Only candidates with an existing legal right to work in the European Union will be considered. #MAKEYourCareerBETTER Interested? Apply now and include your CV (preferably in English) along with a statement confirming your consent to the processing and storage of your personal data. Please be prepared for a live coding session during the interview process, where your technical skills will be thoroughly evaluated.