Research Scientist, CBRNE AI Safety

Summary:

Meta is seeking a Research Scientist to join our FAIR Security, Privacy, and Reliability team, focusing on Chemical, Biological, Radiological, Nuclear, and Explosives (CBRNE) safety and preparedness for AI models. In this role, you will conduct research to evaluate and mitigate potential risks associated with AI systems in CBRNE domains, develop safety frameworks, and contribute to Meta's responsible AI initiatives. You will collaborate with cross-functional teams to ensure our AI models are prepared to handle sensitive content responsibly and safely.

Required Skills:

Research Scientist, CBRNE AI Safety Responsibilities:

1. Conduct research on AI model safety in CBRNE domains, including biology, chemistry, radiological, nuclear, and explosives-related content

2. Develop evaluation methodologies and benchmarks to assess AI model vulnerabilities and safety in CBRNE contexts

3. Design and implement safety mitigations and guardrails for AI systems to prevent misuse in sensitive domains

4. Collaborate with policy, legal, and product teams to translate safety research into actionable guidelines

5. Contribute to preparedness frameworks that anticipate and address emerging risks in CBRNE-related AI applications

6. Publish research findings and represent Meta at academic and industry forums on AI safety

7. Partner with external researchers, government agencies, and safety organizations to advance CBRNE safety standards

Minimum Qualifications:

Minimum Qualifications:

1. Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience

2. PhD in biology, chemistry, nuclear science, security studies, or a related field, OR equivalent experience in CBRNE safety research

3. 2+ years of experience in research related to biosecurity, chemical safety, nuclear safety, or weapon non-proliferation

4. Experience with risk assessment methodologies and safety evaluation frameworks

5. Track record of published research or contributions in CBRNE safety, AI safety, or related domains

6. Experience collaborating with cross-functional teams on safety or policy initiatives

7. Due to export control laws and regulations applicable to this role, candidates must be a U.S. citizen or national, U.S. permanent resident (i.e., current Green Card holder), or lawfully admitted into the U.S. as a refugee or granted asylum

Preferred Qualifications:

Preferred Qualifications:

1. Knowledge of dual-use research concerns and responsible disclosure practices

2. Background in red-teaming, adversarial testing, or safety evaluation of AI systems

3. Experience developing safety guidelines or policies for emerging technologies

4. Experience with AI/ML systems and understanding of large language model capabilities and limitations

5. Experience working with government agencies or international organizations on CBRNE preparedness

Public Compensation:

$154,000/year to $217,000/year + bonus + equity + benefits

Industry: Internet

Equal Opportunity:

Meta is proud to be an Equal Employment Opportunity and Affirmative Action employer. We do not discriminate based upon race, religion, color, national origin, sex (including pregnancy, childbirth, or related medical conditions), sexual orientation, gender, gender identity, gender expression, transgender status, sexual stereotypes, age, status as a protected veteran, status as an individual with a disability, or other applicable legally protected characteristics. We also consider qualified applicants with criminal histories, consistent with applicable federal, state and local law. Meta participates in the E-Verify program in certain locations, as required by law. Please note that Meta may leverage artificial intelligence and machine learning technologies in connection with applications for employment.

Meta is committed to providing reasonable accommodations for candidates with disabilities in our recruiting process. If you need any assistance or accommodations due to a disability, please let us know at [email protected].