Researcher, Safety Training, National Security

OpenAI is seeking a researcher to focus on AI safety training and robustness for U.S. government applications, particularly in national security. You will research and implement methods for safety training, develop evaluations, and collaborate with cross-functional teams to ensure safe and reliable AI deployment.

• Research and implement methods for safety training, reinforcement learning, and adversarial robustness
• Develop evaluations and identify model failure modes
• Collaborate with research, engineering, security, and policy partners
• Advance AI safety post-training and robustness
• Focus on national security applications for U.S. government use
• Requires active TS/SCI clearance

• Requires a Ts Sci security clearance.