Raghav Kansal
Senior Deep Learning Scientist at Bexorg, Inc.
New York City Metropolitan Area United States
Summary
👤
Senior🎓
Top SchoolRaghav Kansal is a Senior Deep Learning Scientist with a decade of experience at the intersection of AI and fundamental science, currently building BexFlow, a foundation model for the human brain at Bexorg. He holds a PhD in particle physics from UC San Diego and was a Schmidt AI Fellow at Caltech and Fermilab, where he developed equivariant graph and transformer models deployed at the CERN Large Hadron Collider. His work spans generative modeling, multimodal representation learning, and Lorentz-group equivariant ML, with publications in NeurIPS, ICML, PRL and JHEP and production-grade deployments in high-energy physics. Raghav has a track record of turning physics and biology priors into state-of-the-art simulation and classification systems, and his open-source JetNet dataset and tools have been widely adopted by the ML+Hep community. He is now translating those techniques to brain molecular trajectories and multiomic integration for biotech applications. An experimentalist-turned-ML scientist, he combines hands-on lab experience (neuroscience and quantum optics) with rigorous model-building for scientific discovery.
10 years of coding experience
Island SchoolUniversity of California, San DiegoInternational Baccalaureate, International Baccalaureate at American School of BombayThe American School in Japan
Github Skills (75)
transformers10
alien10
python10
windows10
deep-learning10
gpu10
graph-convolutional-networks10
gpu-acceleration10
linux10
desktop-application10
numpy10
message-passing10
neural-network10
tensor10
physics10
Programming languages (9)
Github contributions (5)
jet-net/JetNet
Oct 2021 - Dec 2022
For developing and reproducing ML + HEP projects.
Contributions:15 releases, 14 reviews, 139 commits in 1 year 2 months
machine-learning
rkansal47/graph-gan
Nov 2020 - Jul 2021
Contributions:1 release, 14 commits, 12 pushes in 7 months
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.