A bit about me.

I'm a Generative AI engineer who spent the last year building production systems for a Dutch insurer — not prototypes, not demos. Systems that handle real customer conversations, get measured against a KPI dashboard every day, and have to keep working when nobody is watching.

What I care about is the gap between a model that looks good in a notebook and one that survives production traffic. That gap is evaluation, guardrails, and a clear line for when the system should say "I don't know" instead of guessing confidently.

Skills