Researcher, Preparedness

About the TeamThe Preparedness team is an important part of the Safety Systems org at OpenAI, and is guided by OpenAI’s Preparedness Framework.Frontier AI models have the potential to benefit all of humanity, but also pose increasingly severe risks. To ensure that AI promotes positive change, the Preparedness team helps us prepare for the development of increasingly capable frontier AI models. This team is tasked with identifying, tracking, and preparing for catastrophic risks related to frontier AI models.The mission of the Preparedness team is to:Closely monitor and predict the evolving capabilities of frontier AI systems, with an eye towards misuse risks whose impact could be catastrophic to our societyEnsure we have concrete procedures, infrastructure and partnerships to mitigate these risks and to safely handle the development of powerful AI systemsPreparedness tightly connects capability assessment, evaluations, and internal red teaming, and mitigations for frontier models, as well as overall coordination on AGI preparedness. This is fast paced, exciting work that has far reaching importance for the company and for society.About the RoleWe are looking to hire exceptional research engineers that can push the boundaries of our frontier models. Specifically, we are looking for those that will help us shape our empirical grasp of the whole spectrum of AI safety concerns and will own individual threads within this endeavor end-to-end. You will own the scientific validity of our frontier preparedness capability evaluations—designing new evals grounded in real threat models (including high-consequence domains like CBRN as well as cyber and other frontier-risk areas), and maintaining existing evals so they don’t stale or silently regress. You’ll define datasets, graders, rubrics, and threshold guidance, and produce auditable artifacts (evaluation cards, capability reports, system-card inputs) that leadership can trust during high-stakes launches.In this role, you'll:Work on identifying emerging AI safety risks and new methodologies for exploring the impact of these risksBuild (and then continuously refine) evaluations of frontier AI models that assess the extent of identified risksDesign and build scalable systems and processes that can support these kinds of evaluationsContribute to the refinement of risk management and the overall development of "best practice" guidelines for AI safety evaluationsYou might thrive in this role if you:Are passionate and knowledgeable about short-term and long-term AI safety risksDemonstrate the ability to think outside the box and have a robust “red-teaming mindset”Have experience in ML research engineering, ML observability and monitoring, creating large language model-enabled applications, and/or another technical domain applicable to AI riskAre able to operate effectively in a dynamic and extremely fast-paced research environment as well as scope and deliver projects end-to-endIt would be great if you also have:First-hand experience in red-teaming systems—be it computer systems or otherwiseA good understanding of the (nuances of) societal aspects of AI deploymentExcellent communication skills and the ability to work cross-functionallyThis role may require access to technology or technical data controlled under the U.S. Export Administration Regulations or International Traffic in Arms Regulations. Therefore, this role is restricted to individuals described in paragraph (a)(1) of the definition of “U.S. person” in the U.S. Export Administration Regulations, 15 C.F.R. § 772.1, and in the International Traffic in Arms Regulations, 22 C.F.R. § 120.62. U.S. persons are U.S. citizens, U.S. legal permanent residents, individuals granted asylum status in the United States, and individuals admitted to the United States as refugees.About OpenAIOpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. We push the boundar ... (truncated, view full listing at source)