About Me

I am a Principal Machine Learning Scientist at Prescient Design, Genentech. My research focuses on high-dimensional inference and sampling, with a particular emphasis on developing probabilistic algorithms for active, machine-guided molecular design. 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.

Research interests

• Decision-making under uncertainty
  • Designing acquisition functions for multi‑objective Bayesian optimization tailored for molecular property spaces with complex correlation structures
  • Productionalizing machine‑guided design of antibodies, small molecules, and molecular glues with specific project desiderata
• Robust inference in high dimensions
  • Nonparametric/semiparametric Bayes, adaptation, targeted learning
  • Post‑hoc calibration methods including conformal prediction
  • Causality‑inspired domain generalization methods for out‑of‑distribution robustness
• Sampling in high dimensions
  • Sampling algorithms for non‑log‑concave distributions
  • Exploring diffusion models as sampling tools for Bayesian inference
  • Hybridizing MCMC with variational methods to balance accuracy and computational cost