Joe Napoli
Principal AI Scientist, DMPK at Genentech
San Francisco, California, United States
Summary
👤
Senior🎓
Top SchoolJoe Napoli is a Principal AI Scientist in DMPK with 11 years of experience applying deep learning, physical chemistry, and molecular simulation to biological problems. He combines a PhD in Theory & Simulation from Stanford and a Columbia BA in Chemistry with hands-on ML engineering—building data pipelines, experiment-tracking, and production-ready graph and transformer models for enzyme engineering and directed evolution. At Genentech and previously as an early ML hire at Aether Biomachines, he has translated simulation and experimental data into actionable insights and robust tooling using PyTorch, PyTorch Geometric, Metaflow, and PyTorch Lightning. His academic work leverages ab initio molecular dynamics to probe proton transfer and hydrogen-bond dynamics, resulting in multiple first-author publications, reflecting a rare blend of theoretical rigor and practical ML systems design. Based in San Francisco, he is passionate about solving physical and biological science questions with data-driven approaches and has a track record of building infrastructure from the ground up to accelerate discovery.
11 years of coding experience
2 years of employment as a software developer
International Baccalaureate Diploma, International Baccalaureate Diploma at South Fork High SchoolBachelor's Degree Chemistry, Bachelor's Degree Chemistry at Columbia UniversityDoctor of Philosophy (Ph.D.) Chemistry - Theory and Computation, Doctor of Philosophy (Ph.D.) Chemistry - Theory and Computation at Stanford University
English, Spanish
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (16)
popularity7
simulation7
prediction6
molecular-simulation5
audio4
logistics4
machine-learning3
cuda3
gpu3
high-performance3
pytorch2
optimization2
tensorflow2
deep-learning2
simulations1
Programming languages (2)
Github contributions (5)
JNapoli/reax
Jun 2015 - Dec 2015
Contributions:31 commits, 27 pushes, 1 branch in 5 months
JNapoli/autoencoda
Jun 2019 - Jul 2019
Deep learning approach for audio featurization and popularity prediction
Contributions:17 PRs, 66 pushes, 12 branches in 1 month
pytorchpredictiondeep-learningapproachmachine-learning
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.