Mid/Senior AI Engineer (m/f/n)

SHIMI Sp. z o.o.

• Experience building and operating backend services with APIs, async, and testing.
• Hands-on experience taking LLM features to production and maintaining them.
• Knowledge of agent/orchestration frameworks, ideally LangGraph.
• Practical experience with retrieval-augmented generation (RAG).
• Experience debugging LLM systems in production including tracing, evaluation, cost, and latency.
• Familiarity with running services in the cloud, specifically on Azure.
• Strong problem-solving, analytical thinking, and technical decision-making skills.
• Fluent in English, proactive communicator, and team player.
• Open-minded, creative, and motivated to advance AI and automation.

Nice to have:

• Experience with Azure OpenAI, AI Search, and App Service.
• Knowledge of infrastructure as code tools like Bicep.
• Mentoring or tech lead experience.

• Build LLM-powered features end to end using LangGraph and ship them as FastAPI services with streaming, persistence, and proper tests.
• Own answer quality by building evaluation datasets, regression suites, and LLM-as-judge checks.
• Manage query context for the model, orchestrate multi-step research loops, and diagnose retrieval, query, or prompt issues.
• Debug production flows using tracing (Langfuse), investigate issues, and manage latency, token, and cost budgets with AI gateway routing.