Keshavan Seshadri is a Senior Machine Learning Engineer in New York with eight years of experience building production ML systems, full-stack applications, and startups. He combines research-grade ML (QM17 physics-based models, BERT, RAG) with hands-on product delivery—shipping a Table-Augmented Generation feature at Prudential to enable natural language querying of complex insurance data and leading an MVP grant-discovery startup from 0 to traction. Comfortable across the stack, he has implemented scalable web UIs, real-time synchronization for thousands of users in the open-source 3Dmol.js project, and cloud-native deployments using Docker, AWS, and CI/CD. His background spans Cornell Tech and IIIT Hyderabad and blends teaching and community work, from classroom tools used by millions to mentorship as a TA. That mix of applied research, entrepreneurial drive, and practical engineering lets him move ideas rapidly from prototype to production.
B.Tech in Computer Science and MS by research in Computational Natural Sciences, Computer Science, B.Tech in Computer Science and MS by research in Computational Natural Sciences, Computer Science at International Institute of Information Technology Hyderabad (IIITH)
Master of Engineering - MEng, Computer Science, Master of Engineering - MEng, Computer Science at Cornell University
Contributions:50 commits, 8 PRs, 41 pushes in 4 months
Contributions summary:Keshavan primarily contributed to the front-end development of the 3Dmol.js viewer, adding new functionalities to the UI through HTML, JavaScript, and CSS. The commits involved creating session management features, including creating, joining, and deleting sessions, alongside the synchronization of the view. The user implemented a URL state change detection mechanism and view synchronization, significantly enhancing the collaborative features of the application.
Attendance System Using Image Recognition using Facenet
Contributions:1 release, 4 PRs, 16 pushes in 4 years 9 months
facenetimage-recognitionpython3
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.