Researcher, Safety Training, National Security
OpenAI · San Francisco
About this role
**Researcher, Safety Training, National Security** **ABOUT THE TEAM** The Safety Training research team advances capabilities for implementing safe behavior in AI models. Focus areas include training nuanced safety behaviors, robustness against bad actors, privacy/security risks, and trustworthiness in safety-critical situations. **ABOUT THE ROLE** Research and train models for U.S. government use with focus on national security applications. Advance safety post-training and robustness while preserving model usefulness and capabilities. **KEY RESPONSIBILITIES** • Research and implement safety training, reinforcement learning, and adversarial robustness methods • Develop evaluations and identify model failure modes • Collaborate with research, engineering, security, and policy teams for safe deployment **REQUIREMENTS** • 4+ years AI safety research experience (RLHF, adversarial training, robustness) • Degree in computer science, machine learning, or related field • Strong deep learning research or engineering skills • Experience improving model safety for deployment • **Active TS/SCI clearance or equivalent required** **ABOUT OPENAI** OpenAI is an AI research and deployment company dedicated to ensuring general-purpose AI benefits all of humanity. We are an equal opportunity employer. [View full posting for additional details and accommodations information]
Listing freshness
CronJobs last confirmed this listing 1h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.