Karl Cobbe
Research Scientist at OpenAI
Palo Alto, California, United States
Summary
🤩
Rockstar🎓
Top SchoolKarl Cobbe is a research scientist at OpenAI with eight years of experience bridging machine learning research and product-grade software engineering. Based in Palo Alto, he progressed from a Machine Learning Fellow to a Research Scientist since joining OpenAI in 2018, contributing at the intersection of cutting-edge ML and deployable systems. His background includes full-stack development and content-generation tooling for education at Art of Problem Solving and mobile platform engineering at Chatous, giving him a rare blend of research rigor and production delivery. Early experience in hardware verification and applied physics cultivated a strong foundation in formal methods, testbench design, and signal analysis. He holds a BS in Computer Science with an AI focus from Stanford and is known for shipping fast, reliable iterations in both research and consumer-facing contexts. Colleagues would describe him as a technically versatile engineer who translates complex research into practical, scalable implementations.
8 years of coding experience
3 years of employment as a software developer
Phillips Exeter AcademyBS Computer Science Artificial Intelligence, BS Computer Science Artificial Intelligence at Stanford University
Github Skills (11)
deep-reinforcement-learning10
pytorch10
benchmark10
openai10
reinforcement-learning10
paper9
deep-learning9
procedural-generation9
procedural8
gradient8
machine-learning1
Programming languages (3)
Github contributions (5)
openai/train-procgen
Dec 2019 - Jun 2020
Code for the paper "Leveraging Procedural Generation to Benchmark Reinforcement Learning"
Contributions:9 commits, 2 PRs, 6 pushes in 5 months
leveragingproceduralreinforcement-learningdeep-reinforcement-learningprocedural-generation
openai/phasic-policy-gradient
Sep 2020 - Dec 2020
Code for the paper "Phasic Policy Gradient"
Contributions:2 commits, 1 push, 1 comment in 3 months
policygradientpolicy-gradientphasic-policy-gradient
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.