Czym będziesz się zajmować? Role overviewWe’re looking for an AI Engineer to design, implement, and maintain agentic systems for our clients. You’ll work across LLMs, orchestration frameworks, and data pipelines to deliver robust, observable, and secure automations.This is not a research-only role, and you won’t be stuck in endless proof-of-concepts. Every project you take on will target production and client systems, with real use cases and measurable impact.You’ll be joining a hands-on team that thrives on solving challenging problems, shipping production-grade systems, and pushing the boundaries of what AI can do in real business environments.What you’ll doDesign and implement agent architectures and multi-step orchestrations in PythonBuild with frameworks and runtimes such as LangGraph, LangChain, n8n, AWS Bedrock, and similar toolsIntegrate and evaluate frontier models, e.g., Google Gemini, OpenAI GPT family, and Anthropic ClaudeDevelop connectors to SaaS and enterprise systems via APIs, webhooks, queues, and eventsImplement tools, memory, retrieval, and planning strategies for reliable agent behaviorAuthor a reference agent template / internal SDK (LangGraph patterns, tool adapters, memory/plan primitives) adopted across agents.

Kogo poszukujemy? 2+ years of hands-on experience building LLM-powered agents or complex automationsStrong Python skills, including async programming, testing, and packagingExperience with TypeScript (in addition to Python) is a plus, as it’s an emerging language in our stackPractical experience with LangGraph and/or LangChain, plus one or more of: n8n, AWS Bedrock, Airflow, Prefect, Temporal, or similar orchestration toolsWorking knowledge of core model ecosystems: Gemini, OpenAI, and Claude (prompting, tool use, structured output, function calling)Solid data foundations: vector stores, embeddings, RAG patterns, chunking, indexing, and data qualitySoftware engineering fundamentals: Git, code reviews, CI, containerization, cloud services (AWS preferred)Familiarity with ADK (Agent Development Kit) or equivalent frameworks for building and standardizing agent behaviorsNice to haveExperience with agents in production: evaluation frameworks, red-teaming, safety filters, rate-limit and cost controlsRetrieval and data management at scale: document processing, ETL, and governanceBackend development: FastAPI, Flask, Node.js, or Go; relational and NoSQL databases (e.g., Postgres, MongoDB) and modern platforms like Supabase