Shivasankaran Pandi
Software Engineer at Tower Research Capital
Town of Brookhaven, New York, United States
Summary
🤩
Rockstar🎓
Top SchoolShivasankaran Pandi is a software engineer with six years of experience building high-performance, low-latency systems and applied ML solutions, currently engineering nanosecond-scale trading infrastructure at Tower Research Capital. He holds an MS in Computer Science from Stony Brook (3.97 GPA) and a B.Tech from IIT Gandhinagar, and has bridged research and production through roles that span cryo-EM image analysis, protein modeling, and intent discovery. Notable contributions include integrating the first protein language model into DeepChem via Google Summer of Code, implementing and testing new PyTorch layers for DeepChem, and designing protein-generation approaches validated with AlphaFold. His work blends distributed systems and GPU programming with practical ML pipelines, emphasizing reproducible benchmarks and performance optimization. Based in Brookhaven, NY, he prefers solving problems at the intersection of systems design and intelligent automation—shipping solutions that are both performant and experimentally grounded. An internet handle of Fluff_E hints at a curiosity-driven, community-minded approach to open source.
6 years of coding experience
3 years of employment as a software developer
Bachelor of Technology(Hons) - BTech, Computer Science, Bachelor of Technology(Hons) - BTech, Computer Science at Indian Institute of Technology GandhinagarMaster of Science - MS, Computer Science, 3.97/4.0, Master of Science - MS, Computer Science, 3.97/4.0 at Stony Brook University
Github Skills (6)
pytorch10
deep-learning10
python10
machine-learning9
testing8
pytest8
Programming languages (3)
Github contributions (5)
deepchem/deepchem
Jan 2024 - Feb 2025
Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology
Role in this project:
Back-end Developer
Back-end DeveloperContributions:27 reviews, 22 PRs, 43 comments in 1 year 1 month
Contributions summary:Shivasankaran implemented a Highway layer in PyTorch for the `deepchem` repository, indicating work related to deep learning model development. They defined the `Highway` and `HighwayLayer` classes, including initialization, forward pass, and documentation. The user also added an example and a pytest for the new `HighwayLayer`, demonstrating a focus on both implementation and testing within the PyTorch framework.
chemistrysciencedrug-discoverydeep-learningbiology
Shiva-sankaran/deepchem
Jan 2024 - Feb 2025
Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology
Contributions:109 pushes, 28 branches in 1 year 1 month
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.