Jonathan Booher
TLM, Post Training at Nuro
California, United States
Summary
🤩
Rockstar🎓
Top SchoolJonathan Booher is a machine learning researcher and engineer with eight years of experience building safe reinforcement learning and imitation learning systems for real-world robotics and autonomous vehicles. Trained at Stanford (BS/MS CS, AI specialization) and mentored in SVL, he has led teams at Nuro to develop world models, RLHF, reward learning, and safe RL for ego planning and closed-loop agent behavior. His work blends research and production: scaling distributed training pipelines, incorporating uncertainty into policies, and improving sim2real transfer for robotic control. Notably, he accelerated RL training stability by over 2x as an intern and repeatedly moves ideas from academic benchmarks into deployed autonomous last‑mile systems. Based in California, he seeks novel ML algorithms that make robotics feel a little like magic while prioritizing safety and real-world impact.
8 years of coding experience
7 years of employment as a software developer
Master's degree Computer Science, Master's degree Computer Science at Stanford University
Github Skills (33)
webots10
robotics10
gazebosim10
robot10
gazebo-simulator10
reinforcement-learning9
benchmark9
simulation9
manipulation9
simulation-framework9
modularity9
robot-simulator9
mujoco9
autonomous-robots9
pybullet9
Programming languages (1)
Github contributions (5)
jaustinb1/pytorch-CycleGAN-and-pix2pix
Nov 2018 - Apr 2019
Image-to-image translation in PyTorch (e.g., horse2zebra, edges2cats, and more)
Contributions:31 commits, 12 pushes, 1 branch in 5 months
pytorchdeep-learningtranslationcomputer-graphicscomputer-vision
jremmons/ccr-web
Apr 2018 - Aug 2018
Contributions:133 pushes, 2 branches 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.