Senior Research Scientist, AI Biosecurity Assessments

• Project/Division: AI, Applied Research

• Start date:
  As soon as possible

• Status:
  Full-time

• Work location:
  Remote within US, with offices in Cambridge, MA and Berkeley, CA

• Approximate Compensation: $235,000 – $300,000, based on experience. This assumes a Cambridge or Berkeley location; salary will be adjusted based on geographic location and cost-of-living

• Reports to:
  Head of Applied Research

Secure Bio is hiring a Senior Research Scientist to work on our safety assessment engagements with frontier AI developers. You will evaluate models for dual-use biological risks before they are released publicly, running technical assessment pipelines, analyzing model behavior, and writing the reports that inform relevant audiences of any risks identified.

These assessments help set safety standards across the industry and are regularly cited in model cards from leading AI labs. We also work closely with policy bodies including the NIST US AI Safety Consortium and the European AI Office to shape how evaluation frameworks are built.

• 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 our public dashboard of trends in capabilities.

• A PhD in pathogen biology, microbiology, virology, or a closely related field. We will consider equivalent depth from other paths, but expect most strong applicants to hold a doctorate. Wet-lab experience is preferred.

• Strategic judgment about how evaluation results map onto real-world biological risk, and about where technical safeguards succeed and 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 with emerging model releases.

• 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 with building and evaluating LLM or agent systems more broadly.

• Familiarity with biosecurity policy, threat assessment, or counter terrorism work.

• Experience working with AI developers, or in a regulated or NDA-heavy environment.

Joining Secure Bio means joining a mission-driven international team dedicated to protecting the world from biological threats. Through in-house research and development and collaborations with experts across academia, industry, and government, we build the tools, technologies, and institutions the world needs to be secure against future biotechnology.

Major projects by the Secure Bio team include Secure Bio Detection for reliable pandemic detection and our work to understand and reduce biological risks from advanced AI
.

Our employee benefits reflect our belief in investing to build the strongest possible team, in which everyone receives the trust and support they need to excel. Our benefits package includes:

Comprehensive healthcare coverage, including health, dental & vision insurance, as well as a yearly mental health allowance for every employee.

Flexible work hours; unlimited paid time off (PTO) for all employees; and minimum 12 weeks fully-paid parental leave.

G…