About

I build production AI systems where the stakes are too high for outputs to be wrong: clinical workflows, legal reasoning, alignment research. My work sits at the intersection of LLM infrastructure and trust: retrieval pipelines, multi-agent orchestration, RLHF, and drift detection. I researched AI alignment at SPAR using Bayesian methods and foundational models in Astronomy at EleutherAI. Published in The Oncologist for genomics research and wrote a book chapter on Agentic AI for clinical reasoning.

Outside of building things, I write about ML from first principles on my blog, covering optimization geometry, generalization theory, and probabilistic modeling with real benchmarks. I am also a competitive chess player and a devoted fan of the Golden State Warriors and San Francisco 49ers. When I am not building things I am grinding tactics on Lichess or watching game film.