Researcher, Safety Training, National Security

Senior Researcher in Safety Training at OpenAI, focusing on national security applications. The role involves researching and implementing methods for safety training, reinforcement learning, and adversarial robustness to ensure AI models are safe and beneficial for U.S. government use.

Skills and focus areas

• safety training
• reinforcement learning
• adversarial robustness
• rlhf
• deep learning research
• deep learning engineering
• model safety
• collaborative research
• policy implementation
• privacy
• security
• trustworthiness