Send a short note about what you are building and where it is stuck. That is usually enough for me to tell you whether I can help — you do not need a finished specification.

Worth mentioning if you know it: what you run today (cloud, on-premise, Kubernetes or not), what the AI workload is supposed to do, whether the data has to stay in Germany or the EU, and roughly when you need it working.

What I help with — LLM serving on Kubernetes with vLLM and LiteLLM, GPU scheduling and cost work, RAG infrastructure on Qdrant, AI observability and per-token cost tracking, EU AI Act and GDPR reviews for self-hosted models, and Spring AI integration into existing Java systems.

Where — Based in Limburg an der Lahn. On-site across the Rhine-Main area: Frankfurt am Main, Wiesbaden, Mainz, Koblenz and Hessen generally. Remote anywhere in Germany.

Response time — I reply within one working day. If your project is not a good fit for me, I will say so directly rather than let it drift.

Prefer email? hi@wesa.dev · Conversations in German or English.