Samir Chowdhury is a Staff Computer Vision Engineer with nine years of experience applying mathematical foundations to real-world perception systems, currently architecting event logging and data infrastructure for John Deere’s autonomous orchard tractors. He moved from theoretical work in topology and network science—where he reduced algorithmic complexity by orders of magnitude during a Stanford postdoc—to building production ML pipelines, model compilation, and fleet-scale data ingestion that unlocked safety milestones and customer pilots. Samir blends deep research chops (PhD in Mathematics) with hands-on engineering: he directed collection and curation of a 20,000-scene point cloud dataset, developed GPU profiling and HIL stress tools, and created the first Docker and CI/CD workflows for onboard perception model releases. Based in the Bay Area, he uniquely straddles cutting-edge algorithmic speedups and pragmatic systems design, focusing now on scalable AI infra that turns autonomy events into continuous learning for a live fleet.
9 years of coding experience
4 years of employment as a software developer
Bachelor’s Degree, Engineering Science, Mathematics, Bachelor’s Degree, Engineering Science, Mathematics at Tufts University
Doctor of Philosophy (Ph.D.), Mathematics, Doctor of Philosophy (Ph.D.), Mathematics at The Ohio State University
Postdoctoral Scholar, Computational Psychiatry, Postdoctoral Scholar, Computational Psychiatry at Stanford University
Code for computing Hypergraph Co-Optimal Transport distances
Contributions:6 commits, 6 PRs, 12 pushes in 1 year 1 month
distancestransportcomputinghypergraphoptimal
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.