Evaluate AI models for dual-use biological risks, run assessment pipelines, analyze data, and produce technical reports to inform stakeholders.
Locations (3)
United States
Cambridge, Massachusetts, United States
Berkeley, California, United States
Responsibilities
Work with AI firms and internal research and engineering teams to carry out high quality, informative capability and safeguard assessments of emerging AI models.
Execute evaluation pipelines, analyze data and identify how results align with relevant threat models and risk levels.
Manually assess models for both willingness and knowledge across specialized domains of biology.
Synthesize findings into clear evaluation reports, technical write-ups, and risk summaries for partners and regulatory bodies.
Contribute to papers, reports, and trends in capabilities.
Requirements
PhD in pathogen biology, microbiology, virology, or a closely related field
Nice to have: coding experience in industry or graduate research
Nice to have: biosecurity policy familiarity
Nice to have: counterterrorism work
Nice to have: experience in regulated or NDA-heavy environment
