Artificial intelligence
10 OpenAI reinforcement learning researchers
These ten current OpenAI reinforcement learning researchers have held research roles at the company that involve reinforcement learning. A reader can learn what reinforcement learning research at OpenAI involves from people who have done it.
Professionals to explore
01—10Adrien Ecoffet
LinkedInExperience: Research Scientist · OpenAI
Research Scientist at OpenAI since 2020; their profile summary describes them as a deep reinforcement learning researcher and lists the paper Reinforcement Learning Under Moral Uncertainty. Adrien Ecoffet was Research Scientist at Uber (2019–2020) and AI Resident at Uber (2018–2019).
Daniel A. Roberts
LinkedInExperience: Former Lead (Foundations of Reinforcement Learning) · OpenAI
Lead (Foundations of Reinforcement Learning) at OpenAI (2025–2026) and Technical Lead (Science of Reinforcement Learning) at OpenAI (2025); Daniel A. Roberts has been Lead (Frontiers) at OpenAI since 2026 and is listed as Visiting Scientist at Massachusetts Institute of Technology since 2020.
Ilya Kostrikov
LinkedInExperience: Member of Technical Staff (Research Scientist) · OpenAI
Member of Technical Staff (Research Scientist) at OpenAI since 2023; a highlight describes RLHF research and deployment for ChatGPT, including LLM post-training, evaluations and tool use. Ilya Kostrikov was Postdoctoral Scholar at University of California, Berkeley (2021–2023).
James R Lee
LinkedInExperience: Member of Technical Staff · OpenAI
Member of Technical Staff at OpenAI since 2024, a role a highlight ties to deep reinforcement learning, synthetic data and autonomous research, and Research Lead at OpenAI since 2025. James R Lee was Professor of Computer Science at University of Washington (2006–2025).
Joost Huizinga
LinkedInExperience: Research Scientist · OpenAI
Research Scientist at OpenAI since 2020; a highlight says their focus has been on sparse and deceptive problems in reinforcement learning, with progress on the Montezuma's Revenge and Pitfall exploration benchmarks. Joost Huizinga was Research Scientist at Uber (2018–2020).
Kevin Wang
LinkedInExperience: Member of Technical Staff · OpenAI
Member of Technical Staff at OpenAI since 2025, a role a highlight describes as research on RL and reasoning. Kevin Wang was ML Researcher at Princeton Language and Intelligence (2023–2024) and Quantitative Research Intern at Citadel Securities (2024).
Masatoshi Uehara
LinkedInExperience: Member of Technical Staff · OpenAI
Member of Technical Staff at OpenAI since 2026, a role a highlight ties to RL and reasoning for life science. Masatoshi Uehara is also listed as Research Scientist at EvolutionaryScale since 2025 and was Researcher at Genentech (2023–2025), according to their profile.
Sivakanth Gopi
LinkedInExperience: Member of Technical Staff · OpenAI
Member of Technical Staff at OpenAI since 2025; a highlight says they are a researcher at OpenAI working on reinforcement learning. Sivakanth Gopi was Principal Researcher at Microsoft (2023–2025) and Senior Researcher at Microsoft (2020–2023), according to their profile.
Tai Vu
LinkedInExperience: Member of Technical Staff, Research · OpenAI
Member of Technical Staff, Research at OpenAI since 2026, where a highlight says they specialize in LLM post-training, reinforcement learning and agent research. Tai Vu was Senior Machine Learning Engineer at Meta (2022–2026), according to their profile.
Wei Hua Xiong
LinkedInExperience: Member of Technical Staff · OpenAI
Member of Technical Staff at OpenAI since 2026; a highlight says their research focuses on reinforcement learning and its applications in LLM post-training. Wei Hua Xiong is also listed as PHD Candidate at University of Illinois Urbana-Champaign since 2023.
Choose the right perspective
Match the person's research focus to your question, since post-training, RL theory, exploration and applied reasoning work differ a lot. Check when they joined OpenAI and where they worked before, since that shapes the perspective they bring.
Questions to take into the conversation
- 01How does reinforcement learning research for language models differ from classic RL work on games or robotics?
- 02What makes a reward signal or evaluation trustworthy enough to train against?
- 03Which open problems in reinforcement learning for large models seem most important to you right now?
Reaching OpenAI reinforcement learning researchers
How can I contact one of these OpenAI reinforcement learning researchers?
Pick one of the 10 people on this page and choose "Book a paid call", or describe your project to find others. You offer a fee for a 15-minute call or a written answer, Instant Expert finds the person's work email and sends the invitation, and they decide whether to accept. The list covers 1 company: OpenAI, based on profile data retrieved on October 15, 2026. Being listed here doesn't mean someone has agreed to take calls.
How much does it cost to reach OpenAI reinforcement learning researchers?
You choose the offer, starting at $5 per person. The offer is what the person receives, and Instant Expert's fee is added on top, so a $100 offer costs you $125. The fee is 20% of what you pay. You're charged only when the person books the call or sends the answer.
What if they don't reply?
You pay nothing. Instant Expert sends follow-up reminders, and if the person hasn't booked or answered within 7 days, the request expires and any hold on your card is released. You can invite several of the 10 people on this list at once and cap your total spend, so you pay only for the ones who accept.
Can an AI agent ask one of these OpenAI reinforcement learning researchers a question?
Yes. An agent with a USDC wallet on Base can ask one question without an Instant Expert account. It names the person, for example by the LinkedIn URL on this page, and pays per ask over x402 (HTTP 402). The person answers in writing or by voice note, and if nobody answers within 7 days, the payment goes back to the wallet automatically. x402 docs
About this directory
This is a professional research starting point based on business profile data retrieved on . Titles and companies reflect that source snapshot; roles marked former had ended by then. Check the linked profiles for current details. Inclusion does not imply Instant Expert membership or availability.
Request a correction or removal