Bharath Ramsundar
Founder at deepforestsci
San Francisco Bay Area United States
Summary
🤩
RockstarBharath Ramsundar is the founder of Deep Forest Sciences and creator of DeepChem, a widely used open-source toolkit for applying deep learning to drug discovery, quantum chemistry, materials science, and biology. With a Stanford CS PhD focused on deep drug discovery and 14 years of experience, he blends rigorous research with hands-on engineering to push ML into real-world scientific problems. Based in the San Francisco Bay Area, he has authored technical books for O'Reilly and previously co-founded Computable, demonstrating both product and academic leadership. His GitHub contributions emphasize maintaining and improving DeepChem—cleaning code, fixing bugs, and experimenting with models like Atomic Conv—showing a preference for practical, reproducible scientific code. Colleagues describe him as a builder who bridges academic breakthroughs and developer-friendly tooling, making advanced methods accessible to practitioners. His background suggests a rare mix of entrepreneurial grit, deep domain expertise, and commitment to open science.
15 years of coding experience
Stackoverflow
21reputation
143reached
5answers
0questions
Github Skills (11)
machine-learning10
tensorflow10
python10
data-science10
regression9
code-cleanup8
classification8
keras6
rdkit6
deep-learning6
jupyter-notebook6
Programming languages (16)
Github contributions (5)
deepchem/deepchem
Sep 2015 - Sep 2022
Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology
Role in this project:
Data Scientist & ML Engineer
Data Scientist & ML EngineerContributions:17 releases, 2352 reviews, 1676 commits in 7 years 1 month
Contributions summary:Bharath's commits primarily involve cleaning up and fixing bugs in the DeepChem codebase. The changes include cleaning up code, addressing bug fixes within existing code, and renaming a data featurizer. In addition, they are experimenting with and updating a variety of models, including one based on Atomic Conv and the testing of the effects of various loss function adjustments.
deep-learningquantum-chemistrydrug-discoverybiologymaterials-science
rbharath/deepchem
Nov 2016 - Sep 2018
Deep-learning models for Drug Discovery and Quantum Chemistry
Contributions:10 commits, 1 PR, 573 pushes in 1 year 10 months
deep-learningquantum-chemistry
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.