AI / GenAI Engineer · Berlin
AI makes shipping fast — and fast usually means slop. I pair AI as a multiplier with the engineering depth to understand, control, and productionize the output. RAG systems, data platforms, agent governance — held to one standard: determinism, enforced invariants, measurable quality.
Work
End-to-end knowledge and retrieval layer for a production RAG assistant — a deterministic 18-stage ingestion and chunking pipeline, structure-aware indexing for AWS Bedrock, two-stage retrieval with reranking, and a four-pillar evaluation harness.
A spec-driven engine that generates SAP-HANA warehouse objects from YAML and parses existing ones back — bound by a shared intermediate representation and byte-stable roundtrip tests.
A deterministic framework that makes AI-agent software delivery reproducible, auditable, and approval-gated — a no-LLM kernel, single-shot agents, enforced invariants, and a tamper-evident audit log.
A controllable, EU-sovereign environment for agentic coding: LiteLLM tier-routing across local, EU, and AWS Bedrock providers, an adversarial reasoning/execution gate, and a single gateway guardrail.
What I'm looking for
Full-time AI / GenAI Engineering roles with end-to-end ownership — building systems that ship to production, not prototypes that stall. RAG and LLM/agent systems, plus the data and evaluation infrastructure that makes them trustworthy.
Hiring for a GenAI / AI Engineering role, or want to talk systems? Get in touch.
General information, not legal advice · see the eval