I am a computational scientist based in San Francisco, working at the intersection of AI, physics and scientific computing.

In March 2026, I joined Periodic Labs, a startup building AI tools for the physical sciences.

Before that, I spent a decade at Google Research, where I conceived and led NeuralGCM, the first AI-based model to improve on traditional physics-based 15-day weather forecasts and atmosphere-only climate simulations. Earlier work at Google included a multi-year program on accelerating fluid simulations with deep learning, and contributions across drug discovery, microscopy, nanophotonics, quantum chemistry, structural engineering, flood modeling and fundamental physics.

I’m also a long-time contributor to the open source scientific Python stack. I created Xarray — now downloaded ~5m times per week — and previously served on the NumPy steering council.

I am a physicist by training, with a Ph.D from UC Berkeley and a B.A. from Swarthmore College.