EmergingAI biosecurity and scientific misuse assessment

AI Biosecurity Evaluator

Also called Biological Capability Evaluator

An AI Biosecurity Evaluator tests whether a model gives meaningful uplift towards biological harm, under secured conditions. They give the company evidence for release and safeguard decisions, and a clear account of what that evidence cannot tell us.

What they do

They design and run controlled evaluations of how a model handles biological questions and tasks. They agree the threat questions with biosecurity and safety colleagues, build test sets and scoring methods, and run them in a secured setting with restricted access. They read outputs closely, separate real risk signals from noise, and test whether safeguards hold up under pressure. They write up findings, record what the evaluation could not cover, and brief the people who make release decisions. Much of this work sits today inside safety, policy or research titles.

What a strong hire delivers

In the first months, a strong hire gives the company an evaluation approach it can trust and repeat. They set out which risks matter most for the models in question, run a first controlled evaluation, and produce a limitations report that decision makers can read without a specialist beside them. They also set up handling rules for sensitive material and a clear route for escalating serious findings.

How you can tell they are good

Ask them to walk through an evaluation they designed or ran, and what they would change. Good candidates explain why they measured what they did, how they handled sensitive content, and where the results were weak. Ask what a result would need to look like before they raised an alarm. Be wary of anyone who overstates certainty or treats a clean result as proof of safety.

Why it is hard to fill

Almost nobody has this title, so searching by it finds very little. The skills sit across biosecurity, biosafety, life sciences and model evaluation, and few people hold both halves. Many of those who do are bound by confidentiality and cannot describe their work openly. Candidates also need judgement and discretion, which a CV rarely shows. Expect a slow, referral-led search.

Where to find them

Look first at people in biosecurity and biosafety who have moved towards AI, and at model evaluators with a life sciences grounding. Relevant titles include red team lead, safety researcher, threat assessment analyst and biological risk specialist. They tend to work in frontier labs, safety institutes, government-linked assessment teams, research organisations and specialist evaluation firms.

Indicative pay

Not enough published evidence yet to give a fair range for this role, which is common for work this new. We benchmark it for you as part of a search.

Interview questions for an AI Biosecurity Evaluator

  1. Describe a capability evaluation you designed or ran. What question was it meant to answer, and how did you decide it was valid?

    A strong answer names the threat question, the test design, the scoring method and the known weaknesses. It shows they checked validity rather than assuming it. Worry if they only describe running someone else's test or cannot state its limits.

  2. How do you handle sensitive outputs and materials during an evaluation?

    Look for access controls, need-to-know sharing, clear storage and disposal rules, and agreed escalation routes. They should treat handling as part of the design. Worry about casual attitudes, or rules invented only after something sensitive has surfaced.

4 more questions, with what a strong answer covers, are in the Role Kit.

Job description you can post

We are hiring an AI Biosecurity Evaluator to assess whether our models could give meaningful help towards biological harm. You will work in a secured setting with safety, policy and research colleagues, and your findings will inform decisions about release and safeguards.

What you will do

  • Design controlled evaluations of biological capability risk in our models
  • Run evaluations in a secured environment and analyse the results
  • Test the strength of safeguards against varied adversarial approaches
  • Write capability evaluation and limitations reports for decision makers
  • Agree threat questions and scope with safety and biosecurity colleagues
  • Maintain handling rules for sensitive material and escalate serious findings
  • Improve evaluation methods as models and risks change

What you will bring

  • Demonstrated evaluation or red teaming work on biological or closely related risks
  • Working knowledge of biology, biosecurity or biosafety, shown through real projects
  • Experience designing studies with clear scoring and stated limitations
  • Sound judgement and discretion with sensitive information
  • Clear written reporting for non-specialist readers
  • Ability to work with researchers and policy colleagues

Nice to have

  • Experience with model evaluation methods and agent frameworks
  • Prior work with authorised assessment or government-linked programmes
  • Experience testing safeguards in deployed systems

Free to use and adapt. If it saves you time, a link back to this page is appreciated.

Skills that matter

  • Scientific domain expertiseAdvancedApply disciplinary theory and experimental standards
  • AI red teamingAdvancedTest systems adversarially under authorisation
  • AI risk managementWorkingIdentify, assess, treat and monitor AI risks
  • Model evaluationWorkingMeasure capability and failure modes credibly

Other roles in aI biosecurity and scientific misuse assessment

EmergingAI Biosafety SpecialistAn AI Biosafety Specialist reviews how AI workflows touch laboratory and biological work, and puts protective procedures in place. They help a…EmergingScientific Misuse Safeguards ResearcherThis person tests whether an AI system's safeguards hold when it is asked for high-consequence scientific help. They give a company evidence that…EmergingAI Biosecurity Policy AnalystAn AI Biosecurity Policy Analyst weighs the options for managing biological risk from AI systems and sets out what is feasible. They help a company…

Related roles in other families

Hiring nowAI Robustness EngineerAI robustness, safety engineering and incidentsAn AI Robustness Engineer tests how a model behaves when inputs change or the world shifts, then builds and checks fixes. It matters because…Hiring nowAI Safety EngineerAI robustness, safety engineering and incidentsAn AI Safety Engineer turns the ways an AI system could hurt users or the business into specific tests and controls. That gives the company evidence…EmergingAI Incident Response LeadAI robustness, safety engineering and incidentsAn AI Incident Response Lead coordinates the response when a deployed AI system fails or causes harm. They contain the damage, find the root cause…EmergingAI Reliability Evaluation ScientistAI robustness, safety engineering and incidentsAn AI Reliability Evaluation Scientist measures how consistently an AI system works and how likely it is to fail on realistic workloads. It gives…

How we wrote this

Role definitions are our own editorial work, checked against occupational classifications, standards, research and employer pages. Titles vary by company, and this is a description of the work, not a job advert.

← AI biosecurity and scientific misuse assessmentAll new job families

Start a search

Hiring an AI Biosecurity Evaluator?

Tell us the work. We find the people already doing it, whatever their job title says, and you meet them already interviewed for your role.