Scholar
Ji Won Park
Google Scholar ID: URG3MMYAAAAJ
Principal Machine Learning Scientist at Prescient Design, Genentech
Citations & Impact
Citations
1,121
H-index
12
i10-index
12
Publications
20
Co-authors
9
list available
Publications
Cited
0
Resume (English only)
Academic Achievements
- Invited talks and panels at various academic conferences such as 'Targeting the multivariate tails in AI-driven molecular optimization' at The Exploration in AI Today Workshop at ICML 2025 in Vancouver, Canada, and 'Uncertainty-guided drug discovery' at From Models to Molecules: AI’s Expanding Roles in Therapeutics, hosted by Novoprotein in South San Francisco, CA.
Research Experience
- Principal Machine Learning Scientist at Prescient Design, Genentech. Research themes include decision-making under uncertainty (AI4Science), multi-objective Bayesian optimization for molecular design, productionalizing ML-guided design of antibodies, small molecules, and molecular glues tailored to project-specific desiderata, among others.
Education
- Ph.D. in Physics from Stanford University, where he worked on hierarchical Bayesian methods for cosmology. Interned at NASA Ames and the Center for Computational Astrophysics at the Flatiron Institute during his Ph.D. Holds B.S. degrees in Mathematics and Physics from Duke University.
Background
- Research interests include high-dimensional inference and sampling, with a particular emphasis on developing probabilistic algorithms for active, machine-guided molecular design. Current research focus is on prediction-centric Bayesian optimization and robust simulation-based inference.
Miscellany
- Based in the San Francisco Bay Area.
