Researcher
Yuri Burda
Current role not listed
Burda helped establish curiosity-driven learning, in which an agent rewards itself for reaching unfamiliar situations when external rewards are scarce.[1] At OpenAI he also contributed to generative models, robust reasoning and methods that train models to produce answers humans can more easily verify.[2][3][4]
Career & education
OpenAI2016-2024
University of TorontoWork and education history is primarily focused on AI-relevant roles and may not be comprehensive.
References
- Reinforcement learning with prediction-based rewards — OpenAIopenai.com
Co-authorship and curiosity-driven exploration using rewards for unfamiliar situations.
- Team++ — OpenAIopenai.com
2016 full-time hiring announcement identifies generative models as Burda’s research focus.
- Let’s Verify Step by Steparxiv.org
Co-authorship and step-level supervision to improve mathematical reasoning.
- Prover-Verifier Games improve legibility of language model outputs — OpenAIopenai.com
Credits Burda; training improves human evaluation of mathematical solutions.
- OpenAI Removes AI Safety Leader Mądry, a Onetime Ally of CEO Altman — The Informationtheinformation.com
Reports Burda’s departure and July 2024 Anthropic start; exact OpenAI departure month is not established.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
Reviewed August 10, 2026 · Checked for accuracy and new information.