Artificial intelligence
10 OpenAI AI safety researchers
These ten current and former OpenAI AI safety researchers have held research roles at the company whose titles or descriptions name alignment, safety, interpretability or adversarial robustness work. A reader can learn how AI safety researchers approach their work at an AI lab like OpenAI.
Professionals to explore
01—10Aleksandar M.
LinkedInExperience: Member of Technical Staff · OpenAI
Member of Technical Staff at OpenAI since January 2025, with a role description that reads Interpretability research. Before joining, the profile lists a Visiting Scientist role at Guide Labs from 2024 to 2025 and work as an Independent Researcher with MATS Research from 2023 to 2024.
Alex Beutel
LinkedInExperience: Member of Technical Staff, Research Scientist · OpenAI
Member of Technical Staff, Research Scientist at OpenAI since June 2023; his profile says he leads OpenAI's Safety Research teams, spanning safety training, robustness, oversight, model policy and interpretability. At Google he was Senior Staff Research Scientist (2021–2023), Staff Research Scientist (2019–2021), Senior Research Scientist (2017–2019) and Research Scientist (2016–2017).
Christopher A. Choquette-Choo
LinkedInExperience: Member of Technical Staff (Research Scientist) · OpenAI
Member of Technical Staff (Research Scientist) at OpenAI since August 2025; his role description covers machine learning alignment research, including safety, security and privacy. He was a Senior Research Scientist (2024–2025) and Research Scientist (2023–2024) at Google DeepMind, and held two Machine Learning Researcher roles at Google between 2020 and 2023.
Gabriel Wu
LinkedInExperience: Member of Technical Staff · OpenAI
Member of Technical Staff at OpenAI since June 2025; his role description reads Alignment research, and his headline is Alignment @ OpenAI. His profile also lists Visiting Researcher at the Alignment Research Center (since 2023), Director of the AI Safety Student Team (2023–2024) and Research Staff at Redwood Research (2023).
Juan Felipe Cerón Uribe
LinkedInExperience: AI Alignment Research Engineer · OpenAI
AI Alignment Research Engineer at OpenAI since May 2022, with the headline AI adversarial robustness @OpenAI; his profile describes him as an industry machine learning engineer turned researcher working to mitigate risks from misaligned AGI. He was a Machine Learning Engineer at Factored from 2019 to 2022 and a Research Intern at the Stanford Existential Risks Initiative in 2021.
Marcus Williams
LinkedInExperience: Member of Technical Staff · OpenAI
Member of Technical Staff at OpenAI since May 2025, based in Sweden; his profile describes him as an AI safety researcher working on deception and reward hacking monitoring and mitigation at OpenAI. He was a Research Scholar at MATS Research in 2024 and an independent AI Alignment Researcher on a Long-Term Future Fund grant from 2023 to 2024.
Mikita Balesni
LinkedInExperience: Member of Technical Staff · OpenAI
Member of Technical Staff at OpenAI since December 2025, with a role description that reads AI alignment and evaluations and a headline about working on alignment of frontier AI. He was a Research Scientist at Apollo Research from 2023 to 2025 and an ML Safety Research Scholar at the Stanford Existential Risks Initiative from 2022 to 2023.
Ollie Matthews
LinkedInExperience: Member of Technical Staff · OpenAI
Member of Technical Staff at OpenAI since October 2025, based in London; his profile headline describes him as an AI safety researcher on the Alignment team at OpenAI. He was a Research Engineer at the AI Security Institute (AISI) from 2024 to 2025 and an AI Safety Researcher at LASR Labs in 2024.
Rai (Michael) Pokorny
LinkedInExperience: Member of Technical Staff · OpenAI
Member of Technical Staff at OpenAI since November 2022, after a Member of Technical Staff (Resident) role there in 2022; the profile lists work at OpenAI on the Superalignment team (scalable oversight) and the Reinforcement learning team. The profile also lists Software Engineer at Google from 2017 to 2021.
Ryan Lowe
LinkedInExperience: Member Of Technical Staff · OpenAI
Former Member Of Technical Staff at OpenAI (2019–2024); his profile says he did research at OpenAI on the safety team, studying reward modeling, and he was also a Research Intern at OpenAI in 2017. He has been Research Ecosystem Lead at the Meaning Alignment Institute since 2025 and was a graduate student at McGill University from 2014 to 2020.
Choose the right perspective
Match the person's research focus to your question, since alignment, interpretability, evaluations, reward hacking and adversarial robustness each use different methods. Note whether the person is still at OpenAI and whether they came from an independent safety organization or a large company lab, because both shape how they compare safety work across settings.
Questions to take into the conversation
- 01How do you decide which safety risks are worth studying before a model is released?
- 02What does a typical alignment or interpretability experiment look like in practice?
- 03What background would you recommend for someone moving into AI safety research from another field?
Reaching OpenAI AI safety researchers
How can I contact one of these OpenAI AI safety 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 8, 2026. Being listed here doesn't mean someone has agreed to take calls.
How much does it cost to reach OpenAI AI safety researchers?
You choose the offer, starting at $5 per person. It includes Instant Expert's 20% fee, so an offer that pays the person $100 costs you $125. 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 AI safety 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 and may describe past or present roles. Check the linked profiles for current details. Inclusion does not imply Instant Expert membership or availability.
Request a correction or removal