Job description

- 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 THE ROLE SecureBio 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. 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 our public dashboard securebio.org of trends in capabilities. QUALIFICATIONS AND SKILLS - 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. PREFERRED - 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 counterterrorism work. - Experience working with AI developers, or in a regulated or NDA-heavy environment. ABOUT SECUREBIO Joining SecureBio 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 SecureBio team include SecureBio Detection securebio.org for reliable pandemic detection and our work to understand and reduce biological risks from advanced AI securebio.org. BENEFITS 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 Comprehensive healthcare coverage, including health, dental & vision insurance, as well as a yearly mental health allowance for every employee. FLEXIBLE WORK SCHEDULE Flexible work hours; unlimited paid time off (PTO) for all employees; and minimum 12 weeks fully-paid parental leave. DEVELOPMENT OPPORTUNITIES Generous professional development opportunities, including fully-paid conference sponsorships and a yearly development allowance for every employee. 401(K) Employer 401(k) match up to 4% of total salary. APPLICATION PROCESS We will review applications on a rolling basis, and are looking for someone to start as soon as possible. After considering your written application, we may ask you to complete a short work test, and invite you to a screening interview. High-performing candidates may be invited to further interviews and/or paid trial tasks. We will also require up to two reference checks. We’re committed to fostering a culture of inclusion, and we encourage individuals with diverse backgrounds and experiences to apply. We especially encourage applications from women, gender minorities, and people of color who are excited about contributing to our mission, and are happy to consider applicants from overseas. We’re an equal opportunity employer. If you need assistance or an accommodation due to a disability, or have any other questions about applying, please contact careers@securebio.org. REFERRAL BONUS We offer a referral bonus of up to $5,500 to individuals who refer successful candidates for this position: To receive these bonuses, we must reasonably believe that you were responsible for referring the candidate to us (e.g. due to you introducing them to us when we didn’t previously know them, or them mentioning you on their application as the reason they heard about the position). - If you refer a candidate that we invite to an in-person work trial, you will receive $1,100; - If the candidate accepts a job offer from us, you will receive a further $4,400, for a total of $5,500. #LI-DNI

Requirements

Must-haves

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
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 https://securebio.org/benchmarks/ of trends in capabilities.
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.
Generous professional development opportunities, including fully-paid conference sponsorships and a yearly development allowance for every employee.
If you refer a candidate that we invite to an in-person work trial, you will receive $1,100;
If the candidate accepts a job offer from us, you will receive a further $4,400, for a total of $5,500.

Nice-to-haves

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.
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 counterterrorism work.
Experience working with AI developers, or in a regulated or NDA-heavy environment.
We offer a referral bonus of up to $5,500 to individuals who refer successful candidates for this position:

Application prep

Use the role’s language and application details while tailoring your materials.

Keywords to mirror

aipythonllm

Platform: ashby
Effort: quick

Benefits

Benefits detected in the listing.

Dental

Vision

401(K)

Pto

Paid Time Off

Parental Leave

Professional Development