Senior Research Scientist, AI Biosecurity Assessments | On Site - Full Time

Xperteez Technology • Cambridge, MA

20h • Remote

About The Position

The Senior Research Scientist, AI Biosecurity Assessments will evaluate emerging AI models for dual-use biological risks before public release. The role involves running technical assessment pipelines, analyzing model behavior, and preparing reports that communicate identified risks to relevant audiences. The scientist will work with AI firms and internal research and engineering teams to assess model capabilities and safeguards, interpret findings against threat models and risk levels, and contribute to research publications and reports.

The position is in the AI, Applied Research division and reports to the Head of Applied Research. It is full-time and can be performed remotely within the US; the organization also has offices in Cambridge, Massachusetts, and Berkeley, California. The anticipated start is as soon as possible.

The organization is a mission-driven international team working to protect against biological threats through in-house research and development and collaboration with experts in academia, industry, and government. Applications are reviewed on a rolling basis. The process may include a short work test, screening and further interviews, paid trial tasks, and up to two reference checks. The employer encourages applicants from diverse backgrounds and experiences, including applicants from overseas, and is an equal opportunity employer.

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 to 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 conduct high-quality, informative capability and safeguard assessments of emerging AI models.
• Execute evaluation pipelines, analyze data, and determine how results align with relevant threat models and risk levels.
• Manually assess models for willingness and knowledge across specialized biology domains.
• Synthesize findings into clear evaluation reports, technical write-ups, and risk summaries for partners and regulatory bodies.
• Contribute to papers, reports, and analysis of trends in capabilities.

Benefits

• Comprehensive healthcare coverage, including health, dental, and vision insurance.
• A yearly mental health allowance for every employee.
• Flexible work hours.
• Unlimited paid time off.
• At least 12 weeks of fully paid parental leave.
• Professional development opportunities, including fully paid conference sponsorships and a yearly development allowance for every employee.
• Employer 401(k) match up to salary.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: Ph.D. or professional degree