Deeptendu Santra
Machine Learning Engineer
Kolkata, West Bengal, India
Summary
🤩
Rockstar🎓
Top SchoolDeeptendu Santra is a machine learning engineer blending six years of hands-on experience at the intersection of physics and ML, currently building open-source SDLC agents in the San Francisco Bay Area. He has applied equivariant graph neural networks to atomic energy prediction and worked on graph and computer-vision problems ranging from SAR image translation to transformer-based medical imaging. A prolific open-source contributor, he has implemented numerical primitives for framework-bridging tooling like ivy (NumPy/Torch frontends) and contributed graph dataset work for Julia’s MLDatasets. His research into compact objects and quark-star parameter estimation reflects a rare physics-to-ML pipeline expertise that informs his modeling choices. Comfortable shipping both research and production code, he also brings technical writing experience that helps clarify complex ML concepts for broader teams. Deeptendu seeks challenges that push model expressivity and scientific discovery in ML-driven domains.
6 years of coding experience
3 years of employment as a software developer
Bachelor of Technology - BTech Electronics and Communications Engineering, Bachelor of Technology - BTech Electronics and Communications Engineering at Institute Of Engineering and Management
Stackoverflow
21reputation
650reached
1answer
1question
Github Skills (16)
math-functions10
pytorch10
math10
python10
numpy10
maths10
machine-learning9
converter8
tensorflow7
aix6
vector6
neural-network6
deep-learning6
shell6
bash6
Programming languages (18)
Github contributions (5)
ivy-llc/ivy
Sep 2022 - Oct 2022
Convert Machine Learning Code Between Frameworks
Role in this project:
Back-end Developer
Back-end DeveloperContributions:65 reviews, 4 commits, 63 PRs in 1 month
Contributions summary:Deeptendu contributed to the implementation of mathematical functions within the NumPy and Torch frontends, specifically adding `nanmin` functionality. The contributions also included adding the `amin` method for the torch frontend. Further work involved elementwise sum and related tests, and adding an atan method for the Torch frontend.
pythontensorflowframework-learningtemplatedata-science
Dsantra92/MLDatasets.jl
Apr 2022 - Mar 2024
Utility package for accessing common Machine Learning datasets in Julia
Contributions:64 pushes, 20 branches in 1 year 11 months
datasetsmachine-learningmachine-learning-datasetsjulia
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.