I am a research fellow in the Center for Computational Mathematics at the Flatiron Institute, where I am a member of the ML@CCM group and ML@FI. I design and analyze probabilistic machine learning methods. I am motivated by real-world scientific constraints and develop methods in close collaboration with scientists across domains, including biology, chemistry, and physics.
I completed a Ph.D. in Computer Science from Princeton University, where I was advised by Ryan Adams and Barbara Engelhardt. I was supported in part by a Google PhD Fellowship in Machine Learning. Previously, I received an A.B. in Computer Science and Statistics from Harvard University, an M.S. in Statistics from the University of Chicago, and an M.A. in Computer Science from Princeton University.
Research interests:
• black-box approximate inference [variational inference, MCMC]
• generative models under misspecification [mixture modeling, graphs]
• ML for science [e.g., material science, genomics]
I am on the 2025–2026 academic job market: [CV]