Senior AI Engineer – Agent Architekt

This is a fully remote position, open to applicants in Germany.

📋 Description

• Production-grade AI-Agent platform utilizing PydanticAI, LiteLLM, and Langfuse RAG-Pipelines with pgvector at scale (including Multi-Tenant Isolation, Index-Rebuilding Strategy, and Hybrid Search).

• Multi-Tenant Token Quota Service along with evaluation frameworks for each tenant.

• Integration of MCP (Model Context Protocol) as a first-class citizen tool.

• Explainable outputs with comprehensive auditability from prompt to output for regulated industries.

• Architectural decisions that are resilient within the banking, insurance, and pharmaceutical contexts.

• Evaluation-driven approach, not based on vibes. Every agent change undergoes an evaluation suite.

• Architecture Decision Records (ADRs) for every significant architectural choice, not buried in Slack threads.

⛳️ Requirements

• 5+ years of experience in Python production engineering.

• Genuine production-level experience with LLMs, including tokens, latency, cost, and evaluation as part of daily operations.

• RAG engineering experience involving pgvector sizing and re-ranking, beyond just "I know LangChain."

• Practical application of LangGraph, PydanticAI, or a comparable agent framework in production.

• Familiarity with LiteLLM, Langfuse, MCP, or a willingness to learn within 2 weeks.

🏝️ Benefits

• You will finally have the opportunity to work alongside like-minded professionals on a truly high-performance solution, rather than simply following directives from above.

• Here, you will operate according to technical best practices rather than what is simply pleasing to management.

• A fantastic team with plenty of freedom in your work.

• You determine your impact!