Summary
Si-han Chen is a Senior Director in Computational Chemistry specializing in AI-driven small-molecule discovery, with eight years of experience building cloud-native platforms and automation pipelines that connect predictive modeling to wet-lab validation. He has a PhD in physical chemistry and a track record of integrating geometric deep learning, language models, and active learning into virtual screening, molecular design, and multi-objective optimization workflows. At Proxima he led a multidisciplinary team, operationalized foundation models for challenging protein–protein interfaces, and built automated data curation pipelines to scale training inputs. His background in molecular dynamics, high-performance C++/CUDA implementations, and physics-informed generative models gives him rare depth across algorithmic research and production ML engineering. Notably, he combines rigorous free-energy methods and ML scoring to deliver experimentally actionable leads, bridging theory and day-to-day medicinal chemistry decision-making. Based in New York, he is known for turning “brutal” drug-discovery problems into pragmatic ML architectures and reproducible discovery loops.
8 years of coding experience
12 years of employment as a software developer
Doctor of Philosophy (Ph.D.) Physical Chemistry, Doctor of Philosophy (Ph.D.) Physical Chemistry at The Ohio State University
Master’s Degree Analytical Chemistry, Master’s Degree Analytical Chemistry at National Tsing Hua University
Chinese, English, Mandarin