What I'm doing now

Currently at Meta, working on AI systems for internal operations teams. Most of my time goes into LLM-based tooling and OR models that have to work — not demo, actually work — in production environments where the cost of being wrong is real.

On the side, I'm deep in SYNTH and sarvis. Both are iOS projects. Both are trying to make your phone smarter about what you're thinking, not just what you're doing.

I'm also spending more time thinking about how AI agents should be structured when the task is open-ended. No clean answers yet.