Ishan Misra
Research Scientist at Facebook AI
Seattle, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolIshan Misra is a Research Scientist at GenAI Research (Meta) with 13 years of experience at the intersection of machine learning, computer vision, and robotics, grounded in a PhD and MS from Carnegie Mellon. He has led generative and visual recognition research at Facebook AI, building on internships at Microsoft and INRIA where he tackled noisy labels, visual question generation, and shape-from-shading. Notable past work includes interactive learning for Visual Question Answering (Learning by Asking) developed under mentorship from leading vision researchers. A dual gold-medalist B.Tech. graduate, he pairs rigorous academic training with production-facing research that spans both foundational models and perceptual systems. Based in Seattle, he blends deep theoretical insight with a track record of cross-institution collaboration and practical impact on accessibility and vision products.
13 years of coding experience
6 years of employment as a software developer
Fergusson CollegeBachelor of Technology (B.Tech.), Computer Science, Gold Medals - one each for highest GPA in graduating batch and Computer Science, Bachelor of Technology (B.Tech.), Computer Science, Gold Medals - one each for highest GPA in graduating batch and Computer Science at International Institute of Information TechnologyMaster of Science - MS, Robotics, Master of Science - MS, Robotics at Carnegie Mellon University
English, Hindi, Marathi
Github Skills (53)
modular10
python10
pointnet10
machine-learning10
numpy10
deep-learning10
self-supervised-learning10
gpu10
supervised-learning10
neural-network10
extensible10
computer-vision10
visual-recognition10
backbone10
depth-estimation9
Programming languages (2)
Github contributions (5)
imisra/esvmTestCPP
Dec 2012 - Oct 2013
Contributions:12 commits in 10 months
pipelinesvmexemplartestingexemplar-svm
facebookresearch/3detr
Sep 2021 - May 2022
Code & Models for 3DETR - an End-to-end transformer model for 3D object detection
Contributions:8 commits, 3 PRs, 7 pushes in 7 months
pytorchend-to-endefficientnetdeep-learningbackbone
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.