Senior Research Scientist, AI Biosecurity Assessments
About The Position
SecureBio is hiring a Senior Research Scientist to conduct safety assessment engagements with frontier AI developers. The role evaluates models for dual-use biological risks before public release by running technical assessment pipelines, analyzing model behavior, and writing reports that inform relevant audiences about identified risks. Assessments help set safety standards across the industry and are cited in model cards from leading AI labs. The team also works with policy bodies, including the NIST US AI Safety Consortium and the European AI Office, to shape evaluation frameworks. The position is part of the AI, Applied Research project/division. It is full-time and remote within the US, with offices in Cambridge, Massachusetts, and Berkeley, California. The approximate compensation is $235,000–$300,000, based on experience, with adjustments for geographic location and cost of living. The start date is as soon as possible, and the role reports to the Head of Applied Research. SecureBio is a mission-driven international team working to protect the world from biological threats. Through in-house research and development and collaborations across academia, industry, and government, it builds tools, technologies, and institutions to address future biotechnology risks. Major projects include SecureBio Detection for pandemic detection and work to understand and reduce biological risks from advanced AI.
Requirements
- A PhD in pathogen biology, microbiology, virology, or a closely related field; equivalent depth from other paths will be considered, though most strong applicants are expected to hold a doctorate.
- Strategic judgment about how evaluation results map onto real-world biological risk and where technical safeguards succeed or fail.
- Deep interest in safeguards and their failure modes, alongside contributory biological capabilities.
- Ability to turn complex technical results into clear, well-structured writing.
- Comfort with short, intensive project cycles and shifting priorities as new models are released.
Nice To Haves
- Wet-lab experience.
- Roughly a year of coding in an industry or graduate research setting, and working fluency in Python.
- Direct experience with the Inspect AI framework, or broader experience building and evaluating LLM or agent systems.
- Familiarity with biosecurity policy, threat assessment, or counterterrorism work.
- Experience working with AI developers or in a regulated or NDA-heavy environment.
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 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 the public dashboard of capability trends.
Benefits
- Comprehensive healthcare coverage, including health, dental, and vision insurance.
- Yearly mental health allowance for every employee.
- Flexible work hours.
- Unlimited paid time off (PTO).
- Minimum 12 weeks of fully paid parental leave.
- Professional development opportunities, including fully paid conference sponsorships and a yearly development allowance.
- Employer 401(k) match up to 4% of total salary.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
Education Level
Ph.D. or professional degree
