Data Scientist, Cybersecurity

• In this role, you'll define security metrics and evaluation frameworks for AI agents, measuring control effectiveness, behavior patterns, and emerging risks.
• Quantify safeguard effectiveness and operational costs to improve controls and reduce unnecessary friction.
• Build data foundations by improving instrumentation, integrating telemetry, and identifying coverage gaps.
• Develop evaluation systems for security findings to assess accuracy, actionability, and real-world impact.
• Design experiments and analyses to evaluate new models and controls, translating insights into security strategy.

• In this role, you'll define security metrics and evaluation frameworks for AI agents, measuring control effectiveness, behavior patterns, and emerging risks.
• Quantify safeguard effectiveness and operational costs to improve controls and reduce unnecessary friction.
• Build data foundations by improving instrumentation, integrating telemetry, and identifying coverage gaps.
• Develop evaluation systems for security findings to assess accuracy, actionability, and real-world impact.
• Design experiments and analyses to evaluate new models and controls, translating insights into security strategy.

OpenAI is a frontier AI research and product company, with teams working on alignment, policy, and security. We post specific opportunities at OpenAI that we think may be high impact. We do not necessarily recommend working at other positions at OpenAI. You can read concerns about doing harm by working at a frontier AI company in our career review on the topic, including concerns about OpenAI in particular. Note that there have also been concerns around OpenAI's HR practices.