Researcher, Frontier Biological and Chemical Risks

Responsibilities

• Identify emerging AI safety risks and new methodologies for exploring their impact
• Build and continuously refine evaluations of frontier AI models to assess identified risks
• Design and build scalable systems and processes to support these evaluations
• Own the scientific validity of frontier preparedness capability evaluations
• Design new evaluations grounded in real threat models, including CBRN and cyber risks
• Maintain existing evaluations to prevent staleness or silent regression
• Define datasets, graders, rubrics, and threshold guidance
• Produce auditable artifacts such as evaluation cards and capability reports
• Contribute to the refinement of risk management and AI safety evaluation best practices

Requirements

• Passion and knowledge regarding short-term and long-term AI safety risks
• Ability to think outside the box with a robust red-teaming mindset
• Experience in ML research engineering or ML observability and monitoring
• Experience creating large language model-enabled applications
• Technical domain expertise applicable to AI risk
• Ability to operate effectively in a dynamic, fast-paced research environment
• Ability to scope and deliver projects end-to-end

Preferred Qualifications

• First-hand experience in red-teaming systems (computer systems or otherwise)
• Understanding of the societal aspects of AI deployment
• Excellent communication skills and ability to work cross-functionally

About the Company

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. We push the boundaries of the capabilities of AI systems and seek to safely deploy them to the world through our products.