Jerry Tworek is a research lead at OpenAI focused on teaching language models to solve STEM and programming problems. OpenAI's o1 contributions page lists him under Leadership (overall) for o1; his homepage describes leading the team that trained LLMs to reason with reinforcement learning for o1, plus earlier primary contributions to Codex and the model behind GitHub Copilot.123
At a glance
- Current role
- Research lead
- Company
- OpenAI
- Sources cited
- 3
- Profile reviewed
Accomplishments
o1 and reasoning
Tworek's site and OpenAI materials credit him with leadership on training models to reason via reinforcement learning, culminating in the OpenAI o1 release. He has also written about subsequent reasoning deployments including o3-related Codex and ChatGPT Agent work.123
Code models
Earlier OpenAI work includes primary contributions to Codex research and training and to the model that powered GitHub Copilot, as documented on his homepage.1
Timeline
Where they work
- OpenAI 102 people in the wiki
Related people
- Jiayi WengAlso at OpenAI
- Bob McGrewAlso at OpenAI
- Arvind NeelakantanAlso at OpenAI
- Ilya KostrikovAlso at OpenAI
- Eric MitchellAlso at OpenAI
- Eiso KantLanguage models · Developer tools
- Ilyas MoutawwakilDeveloper tools · Language models
- Simon WillisonLanguage models · Developer tools
- Walden YanDeveloper tools · Language models
- David BauDeveloper tools · Language models
Suggest a correction or removal
Profiles cover public professional work only, and each statement cites a source. If something is out of date, missing or wrong, tell us and link a source. People can also ask for their profile to be corrected or removed.
References
3 sources · profile reviewed Oct 24, 2026 · data updated Oct 24, 2026