Researcher, Frontier Biological and Chemical Risks

OpenAI • San Francisco, CA

1d • $295,000 - $445,000

About The Position

The Safety Research team at OpenAI is focused on mitigating AI threats to global security that could scale to an extreme level of severity. This involves measurement (monitoring and predicting AI capabilities), mitigation (ensuring safeguards are adequate), and coordination (setting mitigation targets). This is urgent, fast-paced work with far-reaching implications.

This role involves pushing the boundaries of frontier models to shape our empirical grasp of AI safety concerns. You will own the scientific validity of frontier preparedness capability evaluations, designing new evaluations grounded in real threat models (including CBRN, cyber, and other frontier-risk areas) and maintaining existing ones. You will define datasets, graders, rubrics, and threshold guidance, producing auditable artifacts for leadership.

Key responsibilities include identifying emerging AI safety risks and new methodologies, building and refining evaluations of frontier AI models, designing and building scalable systems for evaluations, and contributing to risk management and best practice guidelines for AI safety evaluations.

Requirements

• Passionate and knowledgeable about short-term and long-term AI safety risks
• Demonstrate the ability to think outside the box and have a robust “red-teaming mindset”
• Experience in ML research engineering, ML observability and monitoring, creating large language model-enabled applications, and/or another technical domain applicable to AI risk
• Able to operate effectively in a dynamic and extremely fast-paced research environment
• Able to scope and deliver projects end-to-end
• Must be a U.S. person as defined by U.S. Export Administration Regulations or International Traffic in Arms Regulations.

Nice To Haves

• First-hand experience in red-teaming systems—be it computer systems or otherwise
• A good understanding of the (nuances of) societal aspects of AI deployment
• Excellent communication skills
• Ability to work cross-functionally

Responsibilities

• Work on identifying emerging AI safety risks and new methodologies for exploring the impact of these risks
• Build (and then continuously refine) evaluations of frontier AI models that assess the extent of identified risks
• Design and build scalable systems and processes that can support these kinds of evaluations
• Contribute to the refinement of risk management and the overall development of "best practice" guidelines for AI safety evaluations

Benefits

• OpenAI is an equal opportunity employer, and we do not discriminate on the basis of race, religion, color, national origin, sex, sexual orientation, age, veteran status, disability, genetic information, or other applicable legally protected characteristic.
• Background checks for applicants will be administered in accordance with applicable law.
• Qualified applicants with arrest or conviction records will be considered for employment consistent with those laws.
• Commitment to providing reasonable accommodations to applicants with disabilities.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed