Software engineer working on AI agent evaluation and LLM integration. 4+ years building production software.
- Now: building benchmark tasks and evaluating AI coding agents, finding where they fail and why
- Before: led development of an LLM-powered platform at Localhost Software House; shipped internal tooling at Oliver Wyman
- bskykeywords.com - free Bluesky keyword analytics, 100+ monthly active users (Next.js, TypeScript)
- Travel Agent Job Board - full-stack job marketplace demo (Ruby on Rails, PostgreSQL)
- Gumroad - fixed two production UI bugs, both merged and deployed:
- RedwoodJS - contributor to redwoodjs/graphql


