Sanjiban Choudhury
Member Of Technical Staff at OpenAI
United States
Summary
👤
Senior🎓
Top SchoolSanjiban Choudhury is a researcher-engineer bridging academia and industry with nine years of experience building decision-making and imitation learning systems for robotics and interactive AI. As an Assistant Professor at Cornell and a Member of Technical Staff at OpenAI (with prior senior research roles at Aurora), he focuses on RLHF, IRL, and foundation models that enable agents to self-align through few-shot human and environmental interactions. His work spans theory and production—publishing ICLR and ICML papers on hybrid inverse reinforcement learning and LLM agent reward models while shipping foundation models for self-driving prediction and planning. He’s particularly interested in using privileged AI feedback and process reward models to make multi-turn code generation and continual self-improvement practical. Trained at Carnegie Mellon, he blends rigorous algorithmic foundations with applied system-building across robotics, autonomy, and large-model agents.
9 years of coding experience
10 years of employment as a software developer
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Carnegie Mellon University
Github Skills (7)
latex5
bibtex4
tex4
linux2
3d-reconstruction1
robotics1
information-gain1
Programming languages (5)
Github contributions (5)
portal-cornell/portal-cornell.github.io
Jun 2022 - Dec 2022
Contributions:10 commits, 32 pushes in 6 months
portal-cornell/cs4756-robot-learning-sp24-website
Jan 2024 - May 2024
Contributions:32 pushes, 1 branch in 3 months
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.