I work at Google on Post Training Gemini, where I helped push our model performance to the top of the WebDev Arena and SWE benchmarks.

Core contributor — Gemini 3.0, 2.5, and 2.0.

I’m interested in how we get models to discover and solve new problems that are unknown to us. My current focus is on long-horizon RL and building reliable reward models to guide that exploration.

I also like to write about the quiet ways AI is changing how we think.

LinkedIn / X / Google Scholar / Email

Research

Industry

Thoughts