Senior Data & AI Platform Architect

I work where data architecture and AI meet. I fit best in senior hands-on roles where I own the architecture, lead the technical work, and mentor engineers across teams. Since 2020 I have modeled and shipped enterprise data platforms in insurance, in IoT, and in AI-native products. Before that I worked on embedded systems, high-performance computing, and production software.

I also build Caudra, an open source coding agent for the terminal. I spend most of my working day with coding agents. I kept adding plugins to get the features I wanted. Often I could not build the plugin I needed, because the agent had no hook in the place it needed one. So I built those features into the agent itself. As a hobby I maintain ninfer-4090, my port of NInfer-3090 to the RTX 4090. It runs Qwen3.8-27B on one consumer GPU. Caudra uses it as a local model and as a local decision engine.

I started early. In high school I designed the electronic control system for a patented fire simulation device, from the circuit board to the Windows GUI. I still like to work across the whole stack. At HDI I modeled analytics domains against an enterprise insurance warehouse with Kimball and Data Vault 2.0 patterns. At EdgeIQ I was Senior Data Architect and owned the tenant-facing data model of a multi-tenant IoT platform. It covered device, event, and time-series domains, and a dbt layer kept the analytics contracts stable while the schema underneath changed. The same platform ran a workflow runtime and Kubernetes provisioning controllers. That taught me a data model is only as good as the runtime that has to honour it. I hold an M.Sc. from RWTH Aachen and have a background in probabilistic modeling, which I use to build production systems that handle uncertainty.

I care about operating boundaries as much as features. In my experience, most AI projects fail on the data layer. I have spent as much time on modeling standards, lineage, and transformation contracts as on retrieval, agentic workflows, evaluation criteria, and human review points. Those review points decide when a system acts on its own and when it asks a person. The team that runs a system needs to know what it does, how it fails, and how to recover it.

I am looking for a full-time senior data and AI platform role. I want to own the data platform end to end and lead the hands-on work on modeling, architecture, pipelines, evaluation, infrastructure, and the handover to operations.

Based in Germany. German native, English fluent. Open to DACH, European, and compatible global remote roles, with consulting or advisory work as a secondary path when there is a strong technical fit.