AI Safety Review (Remote, Contract)
This Jobot Consulting Job is hosted by: Augie Ullmann
Are you a fit? Easy Apply now by clicking the "Apply Now" button and sending us your resume.
Salary: $75 - $100 per hour
A bit about us:
We are partnered with a fast growing AI data services company that builds the training and evaluation data behind many of the world's leading AI labs and foundation model developers. Their work sits where technical expertise meets model safety, bringing in specialists from chemistry, biology, radiation science, nuclear engineering and emergency response to evaluate how AI systems handle high consequence subject matter. The experts on these projects shape how frontier models reason about hazard, risk and public safety, and that reach extends well beyond any single laboratory or response program. They operate remotely across time zones and build their review teams around people who are already practicing in their field. We are helping them identify CBRN specialists for this engagement.
Why join us?
Competitive Hourly Compensation: Up to $100/hr as an independent contractor, paid hourly
Keep Your Current Role: Structured as supplemental work, not a career move. No requirement to leave your position
100% Remote, Flexible Hours: Set your own schedule and volume across time zones
Direct Impact on Frontier AI Safety: Your judgment shapes how leading models handle chemical, biological, radiological and nuclear subject matter
Work Inside Your Expertise: Technical review and reference writing in the domain you already practice in, not general purpose data work
Credential Respected, Not Retrained: Built for practicing specialists, with project rubrics rather than a long ramp
Growing Engagement: An expanding program with continued need across all four CBRN domains
Job Details
Key Responsibilities and Duties
Review AI generated responses covering chemical, biological, radiological, nuclear, hazardous material, emergency preparedness and public safety topics for technical accuracy, safety framing and guideline alignment
Flag outputs that provide dangerous procedural detail, acquisition guidance, weaponization support, evasion tactics, unsafe laboratory guidance, harmful exposure advice or other misuse enabling content
Create gold standard reference content that answers benign CBRN questions responsibly without introducing operationally dangerous instruction
Evaluate and rank model outputs on safe handling, correct risk framing, appropriate refusals, helpful redirection, scientific accuracy and clarity
Detect hallucinated claims, incorrect hazard classifications, misleading risk statements, overconfident conclusions, poor escalation guidance and unsafe recommendations
Apply project rubrics consistently and provide clear written feedback explaining why content is safe, unsafe, incomplete or technically incorrect
Ensure CBRN content uses precise terminology and communicates risk without exaggeration or minimization
Escalate ambiguous, high risk or potentially harmful content for additional review per project guidelines
Qualifications Needed
Bachelor's degree or higher in Chemistry, Biology, Microbiology, Public Health, Toxicology, Nuclear Engineering, Radiation Science, Emergency Management, Environmental Health and Safety, Biosecurity, Security Studies or a related field, or equivalent professional experience
Minimum 3 years of professional experience in CBRN safety, emergency preparedness, hazardous materials, biosafety, radiation safety, public health, environmental health and safety, defense or security analysis, or technical review
Experience or strong background in chemical, biological, radiological and nuclear hazard categories, including high level risk assessment, exposure pathways, protective concepts, emergency communication and public safety principles
Strong background in identifying unsafe instructions, operationally enabling detail, inappropriate specificity, misleading hazard claims, inaccurate emergency advice and unsupported technical conclusions
Proven ability to evaluate technical content for accuracy, completeness and policy alignment, and to explain that judgment in precise written English
Professional English proficiency at C1 minimum, sufficient to follow written guidelines and produce detailed written feedback
Familiarity with safety frameworks, emergency response concepts, biosafety levels, hazardous material communication, radiation protection principles, decontamination concepts, incident reporting and public health guidance preferred
Prior experience with AI safety, data annotation, technical QA, policy review, risk assessment, red team review, scientific review or rubric based evaluation strongly preferred
Reliable and self directed, able to deliver consistent quality in an hourly remote contractor workflow
of the United States, United Kingdom, Australia or New Zealand
Interested in hearing more? Easy Apply now by clicking the "Apply Now" button.
Jobot is an Equal Opportunity Employer. We provide an inclusive work environment that celebrates diversity and all qualified candidates receive consideration for employment without regard to race, color, sex, sexual orientation, gender identity, religion, national origin, age (40 and over), disability, military status, genetic information or any other basis protected by applicable federal, state, or local laws. Jobot also prohibits harassment of applicants or employees based on any of these protected categories. It is Jobot's policy to comply with all applicable federal, state and local laws respecting consideration of unemployment status in making hiring decisions.
Sometimes Jobot is required to perform background checks with your authorization. Jobot will consider qualified candidates with criminal histories in a manner consistent with any applicable federal, state, or local law regarding criminal backgrounds, including but not limited to the Los Angeles Fair Chance Initiative for Hiring and the San Francisco Fair Chance Ordinance.
Information collected and processed as part of your Jobot candidate profile, and any job applications, resumes, or other information you choose to submit is subject to Jobot's Privacy Policy, as well as the Jobot California Worker Privacy Notice and Jobot Notice Regarding Automated Employment Decision Tools which are available at jobot.com/legal.
By applying for this job, you agree to receive calls, AI-generated calls, text messages, or emails from Jobot, and/or its agents and contracted partners. Frequency varies for text messages. Message and data rates may apply. Carriers are not liable for delayed or undelivered messages. You can reply STOP to cancel and HELP for help. You can access our privacy policy here: jobot.com/privacy-policy
Employers have access to artificial intelligence language tools (“AI”) that help generate and enhance job descriptions and AI may have been used to create this description. The position description has been reviewed for accuracy and Dice believes it to correctly reflect the job opportunity.
- Dice Id: 91113390
- Position Id: 1550608729
- Posted 2 days ago
