Eric Mitchell
Co-lead of the Post-training Frontiers team (with Yann Dubois) · OpenAI
At a glance. Eric Mitchell is listed as Co-lead of the Post-training Frontiers team (with Yann Dubois) at OpenAI. The profile sits among the builders and open-source contributors. Fields listed: Language models and Reinforcement learning. The source lists 1 official page, 1 listed honor and open-role pages for OpenAI.
Summary
Co-lead of OpenAI's Post-training Frontiers team; co-author of Direct Preference Optimization (DPO).
Known for: Direct Preference Optimization (DPO); DetectGPT.
Works at
- OpenAI 63 people in the wiki
Other documented roles
Not confirmed as current in the source profile.
- PhD student in Computer Science, advised by Chelsea Finn and Christopher D. Manning, Stanford University
Open roles
Related people
- Shixiang Shane GuAlso at OpenAI
- Jakub PachockiAlso at OpenAI
- Bob McGrewAlso at OpenAI
- John SchulmanAlso at OpenAI
- Aravind SrinivasAlso at OpenAI
- Nathan LambertLanguage models · Reinforcement learning
- Mika SenghaasReinforcement learning · Language models
- Edward BeechingLanguage models · Reinforcement learning
- Eiso KantLanguage models · Reinforcement learning
- Denny BritzLanguage models · Reinforcement learning
Source and corrections
Read the full profile on USASI ↗
Facts on this page come from that USASI profile (reviewed Oct 21, 2026); data last checked Oct 23, 2026. See something wrong? Suggest a correction.