I spent 9 years at Amazon figuring out when metrics actually mean something.

Causal inference, experimentation, and GenAI evaluation — written down for people doing the same work. Joining Taskrabbit as Senior Data Scientist in April 2026.

Recent writing

All pieces →
LLM Fundamentals·Apr 2026Latest

RLHF and DPO: Alignment from Human Feedback

How we teach models to be helpful — from reward models and PPO to direct preference optimization and why DPO is simpler.

Stay in the loop

New pieces, straight to your inbox.

Causal inference, experimentation, GenAI. No noise — just the next piece when it's ready.