Research Scientist, CBRNE AI Safety

Meta•Menlo Park, CA

13d•$154,000 - $217,000

About The Position

Meta is seeking a Research Scientist to join its FAIR Security, Privacy, and Reliability team, focusing on Chemical, Biological, Radiological, Nuclear, and Explosives (CBRNE) safety and preparedness for AI models. The role conducts research to evaluate and mitigate potential risks associated with AI systems in CBRNE domains, develops safety frameworks, and contributes to Meta’s responsible AI initiatives. The scientist collaborates with cross-functional teams to help ensure AI models handle sensitive content responsibly and safely.

Requirements

Bachelor's degree in Computer Science, Computer Engineering, a relevant technical field, or equivalent practical experience.
PhD in biology, chemistry, nuclear science, security studies, or a related field, or equivalent experience in CBRNE safety research.
At least 2 years of experience in research related to biosecurity, chemical safety, nuclear safety, or weapon non-proliferation.
Experience with risk assessment methodologies and safety evaluation frameworks.
Track record of published research or contributions in CBRNE safety, AI safety, or related domains.
Experience collaborating with cross-functional teams on safety or policy initiatives.
Must be a U.S. citizen or national, U.S. permanent resident (current Green Card holder), or lawfully admitted into the U.S. as a refugee or granted asylum, due to export control laws and regulations applicable to the role.

Nice To Haves

Knowledge of dual-use research concerns and responsible disclosure practices.
Background in red-teaming, adversarial testing, or safety evaluation of AI systems.
Experience developing safety guidelines or policies for emerging technologies.
Experience with AI/ML systems and understanding of large language model capabilities and limitations.
Experience working with government agencies or international organizations on CBRNE preparedness.

Responsibilities

Conduct research on AI model safety in CBRNE domains, including biology, chemistry, radiological, nuclear, and explosives-related content.
Develop evaluation methodologies and benchmarks to assess AI model vulnerabilities and safety in CBRNE contexts.
Design and implement safety mitigations and guardrails for AI systems to prevent misuse in sensitive domains.
Collaborate with policy, legal, and product teams to translate safety research into actionable guidelines.
Contribute to preparedness frameworks that anticipate and address emerging risks in CBRNE-related AI applications.
Publish research findings and represent Meta at academic and industry forums on AI safety.
Partner with external researchers, government agencies, and safety organizations to advance CBRNE safety standards.