About Me

Ten years shipping commerce platforms. Now applying the same engineering discipline to production AI systems — with the same focus on reliability, observability, and things that actually work.

My career started in e-commerce. A decade later, I'm still in that world — Magento, Adobe Commerce, B2B flows, performance work — but increasingly my clients ask the same question: can AI do this? The answer is usually yes, if you treat it as an engineering discipline rather than a research project.

That thread runs through everything I build now: applying the same production standards that keep commerce sites running during peak traffic — observability, graceful degradation, evaluation, boring infrastructure — to the probabilistic world of large language models. Retrieval pipelines, agent workflows, document automation, evaluation harnesses. The unglamorous parts that determine whether an AI feature survives contact with real users, real data, and real edge cases.

I have worked with mid-size companies across Germany and Europe: manufacturers moving from manual data entry to automated document processing, online retailers modernizing their Magento platforms, and product teams integrating LLM features into existing systems without disrupting what already works.

My working style is direct and async-friendly. I write clearly, give honest technical assessments, and focus on shipping software that solves the actual problem — not the idealized version of the problem. I take on a limited number of projects at a time so each one gets full attention.

If you are working on an e-commerce platform or AI system and want to talk through the technical approach, I am happy to have that conversation.