CBRN Specialist, AI Safety Review

Sovrano AI builds evaluation and training data for frontier AI labs, and this project is about where those models handle hazardous material badly. You take a real user request, look at how the model answered it, and rule on whether the answer was safe, accurate and appropriately framed. Some of what you see will be a model handing out operational detail it should never have given. Just as much of it will be a model refusing a perfectly ordinary question from an emergency planner or a safety officer, and catching that matters as much as catching the dangerous case. The work spans all four hazard classes, and you will be assigned to the strand that matches your background: chemical safety and toxicology, biosafety and biosecurity, radiological protection, or nuclear safety and safeguards. You tell us which in the short survey we send after you apply. This panel is about misuse and safety framing. If your ground is the physics itself, or process engineering, we run separate technical panels you would fit better.

Key responsibilities

• Assess AI answers on chemical, biological, radiological, nuclear, hazardous-material and emergency-preparedness topics for technical accuracy and safe framing.
• Flag content that gives procedural detail, acquisition routes, weaponization support, unsafe lab guidance or harmful exposure advice.
• Flag the opposite failure too: refusals and hedged non-answers on legitimate professional and public-safety questions.
• Work primarily in your own hazard strand, while holding enough breadth to judge a request that crosses two of them.
• Rank competing model answers against each other and say what separates them.
• Write the reference answer: the response that handles a benign CBRN question properly without crossing into operational detail.
• Catch hallucinated claims, wrong hazard classifications, misstated exposure risks, bad escalation advice and overconfident conclusions.
• Apply the project rubric consistently and explain each call in writing.
• Escalate ambiguous or high-risk items for a second review rather than deciding alone.

Ideal qualifications

• Bachelor's degree or higher in chemistry, toxicology, microbiology, biology, public health, health physics, radiation science, nuclear engineering, environmental health and safety, biosecurity, emergency management, security studies or a related field. Equivalent professional experience also counts.
• Three or more years of professional work in at least one of: chemical safety and toxicology, biosafety and biosecurity, radiation protection and health physics, or nuclear safety, safeguards and nonproliferation.
• Depth in your own strand, plus enough working knowledge of the other three to recognize when a request crosses into them.
• A grasp of hazard categories, exposure pathways, protective measures, decontamination, emergency communication and the public-safety principles around all of it.
• The judgment to tell an unsafe answer from a merely uncomfortable one, and the confidence to say so in writing.
• English at C1 or above, since the rubric and all written feedback are in English.
• Based in the US, UK, Canada, Australia, New Zealand or the European Union.

Requirements

• Bachelor's degree or higher in a CBRN-adjacent field, or equivalent professional experience
• Minimum 3 years of professional experience in at least one CBRN strand (chemical, biological, radiological or nuclear)
• Names a primary hazard strand in the expert survey
• Based in the US, UK, Canada, Australia, New Zealand or the European Union
• English at C1 or above, written and verbal
• Passes the expert survey before a bootcamp seat is allocated
• Available for the paid bootcamp on Monday and production from Tuesday
• Able to commit roughly 10 hours inside the first batch window, closing Sunday
• Joins the Sovrano Discord before the bootcamp
• Independent contractor, invoices Sovrano directly

Nice to have

• A professional credential in your strand: CIH, CHP, biosafety officer certification, RSO appointment, Chartered Chemist, or equivalent.
• Practical work with GHS classification, biosafety levels, ALARA and source categorization, or IAEA safeguards.
• Emergency response, incident command or exercise experience.
• Prior AI safety, red-teaming, policy review or rubric-based evaluation work.

What success looks like

• You clear the bootcamp on your own merit and start producing on day one of the batch.
• Your judgment on what is safe to answer, and what is not, matches a senior reviewer's without needing a second opinion.
• Your written reasoning tells a reviewer why an answer is wrong, not just that it is.
• You catch the ordinary professional question the model refused for no good reason, as reliably as you catch the dangerous one it answered.
• You hold the quality bar across the whole batch, including the last task on Sunday.
• You are reachable on Discord during the batch and flag ambiguous cases instead of guessing.

Payment & terms

• $35 to $49 per hour, based on your background. Your exact rate is confirmed in writing before you start the bootcamp. Paid hourly for time worked, as an independent contractor. The first batch is roughly 10 hours of work. A paid bootcamp runs on Monday, production opens Tuesday, and the batch closes Sunday. There is a good chance the work is extended beyond the first batch, and the people who deliver well on it are the ones we go back to. Payment runs through Sovrano directly. You invoice us, we do not file or submit tax forms on your behalf. Fully remote, on your own schedule inside the batch window. No fixed shifts and no standing meetings. How to apply: apply here with your CV or LinkedIn profile, then complete the short expert survey we send you. Shortlisted applicants get the bootcamp invitation and the project guidelines by email.