Nishant Kheterpal
PhD Candidate
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolNishant Kheterpal is a PhD candidate in robotics focused on provable safety for automated vehicles, combining a decade of experience across research and engineering in autonomy and simulation. He has shaped traffic-focused reinforcement learning tools (notably contributions to the Flow project) and studied system-level safety metrics during a research internship at Uber ATG. Prior roles include building simulation stacks for autonomous trucking at Ike and hands-on control and energy modeling work at GM and Apple, giving him a rare blend of theory, simulation, and vehicle systems expertise. A UC Berkeley EECS alum with strong academic publishing experience, he also taught data-driven computation and designed RL experiments for mixed-autonomy traffic—skills that translate to rigorous, reproducible research and production-ready simulation code. Based in San Francisco, he’s as comfortable implementing lane-change models in Flow as he is talking about cars over coffee.
10 years of coding experience
5 years of employment as a software developer
Bachelor’s Degree, Electrical Engineering and Computer Sciences, 3.84, Bachelor’s Degree, Electrical Engineering and Computer Sciences, 3.84 at University of California, BerkeleyDoctor of Philosophy - PhD, Robotics, Doctor of Philosophy - PhD, Robotics at University of MichiganHigh School, High School at Skyline High School
Github Skills (10)
controls10
machine-learning10
traffic10
congestion-control10
python10
reinforcement-learning10
api-design9
machine-learning-models9
api9
apim9
Programming languages (10)
Github contributions (5)
flow-project/flow
Feb 2017 - Dec 2018
Computational framework for reinforcement learning in traffic control
Role in this project:
Backend Developer & ML Engineer
Backend Developer & ML EngineerContributions:279 commits, 11 PRs, 8 pushes in 1 year 10 months
Contributions summary:Nishant made several changes to the codebase focused on reinforcement learning and traffic control. Their contributions include modifying existing environment configurations related to velocity and car following models, as well as implementing a new Optimal Vehicle Model controller. Furthermore, they are implementing lane changing models. These changes indicate an active role in developing and refining the core logic and algorithms driving the project's core functionality.
autonomousreinforcement-learningvehicle-controldeep-reinforcement-learningbenchmark
nskh/automatic-safety-proofs
Jun 2021 - Feb 2025
Contributions:5 reviews, 10 PRs, 50 pushes in 3 years 8 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.