Summary
Jay Patravali is a Senior Data and Applied Scientist at Microsoft with 11 years of experience building computer vision and ML systems across research and production, specializing in geospatial intelligence for on-prem, cloud, and edge deployments. His background spans academic robotics and perception research to industry work on large-scale video self-supervision, few-shot video classification, and medical and pose modeling, with publications at ICCV, WACV, MICCAI, and CVPR workshops. He has repeatedly bridged research and engineering—turning novel probabilistic and unsupervised methods into robust prototypes and services for Azure and product teams. Comfortable across the stack, Jay combines systems integration and tooling with algorithm design, having shipped vision-based localization for autonomous platforms and diagnostics for cardiac MRI. Based in Seattle, he is driven by annotation-efficient representation learning and practical ML that survives noisy, real-world sensing. A less obvious strength is his consistent track record of translating high-risk research (e.g., million-scale video self-supervision) into reproducible, production-ready pipelines.
11 years of coding experience
8 years of employment as a software developer
Master of Science - MS Robotics, Master of Science - MS Robotics at Oregon State University
Bachelor of Technology (BTech) Electronics and Communications Engineering, Bachelor of Technology (BTech) Electronics and Communications Engineering at Vellore Institute of Technology
ICSE, ICSE at Smt Sulochanadevi Singhania School
Marathi, German, Hindi, English