About Me

I am a Principal Scientist and Group Lead at Prescient Design, Genentech, developing statistical frameworks for reliable decision making using large models, with applications to model‑guided scientific discovery. My research focuses on uncertainty quantification, Bayesian experimental design, and scalable inference, emphasizing methods that provide formal guarantees, are sample‑efficient, and improve with advances in foundation and generative models. I received my Ph.D. in Physics from Stanford University, where I worked on hierarchical Bayesian methods for cosmology. During my Ph.D., I interned at NASA Ames and the Center for Computational Astrophysics at the Flatiron Institute. I hold a B.S. in Mathematics and a B.S. in Physics from Duke University.

Recent events

• January 20, 2026: Invited talk "Lab-in-the-loop therapeutic antibody design" - Biologic Summit 2026 in San Diego, CA
• November 13, 2025: Invited talk "Antibody DomainBed: out-of-distribution generalization in therapeutic protein design" - PEGS Europe 2025: Machine Learning for Protein Engineering in Lisbon, Portugal
• November 12, 2025: Invited talk "Lab-in-the-loop application for clinically relevant antigen targets" - PEGS Europe 2025: Machine Learning for Protein Engineering in Lisbon, Portugal
• July 19, 2025: Invited talk and panel "Targeting the multivariate tails in AI-driven molecular optimization" - The Exploration in AI Today Workshop at ICML 2025 in Vancouver, Canada
• May 19, 2025: Invited talk "Uncertainty-guided drug discovery" - From Models to Molecules: AI’s Expanding Roles in Therapeutics, hosted by Novoprotein in South San Francisco, CA