Chemical Safety Expert for AI Model Safety Audit
Remote in 8 countries
Malta, Netherlands, Poland, Portugal, Romania, Sweden, Slovenia, Slovakia
SpaceJobs.Now is free for job seekers. Some links here pay us: a staffing agency, shift app, training program, course or store may pay us when you join or buy through our link, and a job ad network pays us when you click or apply to a job it carries (we mark those as sponsored or say so beside Apply). A job whose link pays us can be shown higher in a list. None of this costs you anything or changes what you are paid, and no employer can buy a spot or a featured place here.
Open in 1 location
SuperAnnotate (SME) posts this job as separate openings, each with its own application: the team, schedule and pay can differ between them.
Malta
1 open- up to $70/hr
Malta (Remote) (opens in new tab)
Contract · Posted 1mo ago
Netherlands
1 open- up to $70/hr
Netherlands (Remote) (opens in new tab)
Contract · Posted 1mo ago
Poland
1 open- up to $70/hr
Poland (Remote) (opens in new tab)
Contract · Posted 1mo ago
Portugal
1 open- up to $70/hr
Portugal (Remote) (opens in new tab)
Contract · Posted 1mo ago
Romania
1 open- up to $70/hr
Romania (Remote) (opens in new tab)
Contract · Posted 1mo ago
Slovakia
1 open- up to $70/hr
Slovakia (Remote) (opens in new tab)
Contract · Posted 1mo ago
Slovenia
1 open- up to $70/hr
Slovenia (Remote) (opens in new tab)
Contract · Posted 1mo ago
Sweden
1 open- up to $70/hr
Sweden (Remote) (opens in new tab)
Contract · Posted 1mo ago
About the job
Description
SME Careers is hiring chemists and chemical safety professionals to audit how AI models respond to sensitive questions in the field. Each task gives you a user request and the answers three different models gave to it. You classify the request (benign, dual-use or adversarial), mark each answer as safe or unsafe and say why, rank the three against each other, and write the answer the model should have given. For dual-use requests you also note what makes it sensitive, what legitimate purpose it serves, and who should be able to get an answer.
The requests are realistic: what synthetic and analytical chemists, toxicologists, industrial hygienists, process safety engineers, regulators and occasionally bad actors actually ask. Some are ordinary professional questions that models wrongly refuse, and catching those matters as much as catching the dangerous ones.
Who we're looking for
Synthetic and analytical chemists; toxicologists and pharmacologists; industrial hygienists and chemical safety/process safety professionals; CWC or chemical-security specialists; hazmat, poison-control or chemical incident responders; and chemical regulators (EPA, OSHA, HSE, OPCW-adjacent, or equivalent). Usually a relevant degree plus five or more years of professional experience. Experience with safety data sheets, exposure assessment, incident reports or regulatory review is a strong plus.
Before you apply
Open only to citizens or permanent residents of the US, UK, Canada, Australia, New Zealand and the European Union.
Responsibilities
- Develop AI Training Content: Create detailed prompts in various topics and responses to guide AI learning, ensuring the models reflect a comprehensive understanding of diverse subjects.
- Optimize AI Performance: Evaluate and rank AI responses to enhance the model's accuracy, fluency, and contextual relevance.
- Ensure Model Integrity: Test AI models for potential inaccuracies or biases, validating their reliability across use cases.
Requirements
- Bachelor’s degree or higher in Chemistry, Chemical Engineering, Toxicology, Environmental Health & Safety, Industrial Hygiene, Hazardous Materials Management, or a closely related field; advanced degree or professional safety certification is a strong plus.
- 3+ years of professional experience in chemical safety, laboratory safety, hazardous materials handling, EHS, toxicology, industrial hygiene, chemical risk assessment, regulatory compliance, or related technical safety work.
- Strong understanding of chemical hazards, including toxicity, corrosivity, flammability, reactivity, incompatibilities, exposure routes, storage risks, spill response principles, PPE, ventilation, and safe handling practices.
- Familiarity with chemical safety documentation and frameworks such as Safety Data Sheets, GHS hazard communication, labeling, exposure limits, risk assessments, SOPs, and incident escalation procedures.
- Ability to review AI-generated chemical safety content for technical accuracy, safety alignment, misuse risk, hallucinated claims, inappropriate specificity, and potentially dangerous procedural guidance.
- Strong judgment in distinguishing between safe educational content and content that could enable unsafe chemical handling, synthesis, misuse, evasion, or harmful experimentation.
- Excellent written English skills, with the ability to provide clear, structured feedback explaining why a response is safe, unsafe, incomplete, misleading, or technically incorrect.
- High attention to detail when reviewing chemical terminology, units, concentrations, exposure assumptions, hazard classifications, safety controls, and emergency-response guidance.
- Comfortable applying detailed project rubrics consistently across ambiguous or sensitive chemical safety scenarios.
- Prior experience with AI safety, red-team review, model evaluation, content moderation, data annotation, technical QA, scientific review, or rubric-based evaluation is preferred.
Where you can work from
This job is 100% remote, for applicants who live in these 8 countries: Malta, the Netherlands, Poland, Portugal, Romania, Sweden, Slovenia and Slovakia.
From SuperAnnotate (SME)'s job posting for Slovakia (Remote), checked 10 Nov 2026. The employer's own page is the final word on requirements and availability. This is work on AI systems for an AI company, not for a space employer: never share export-controlled or proprietary technical data in a task, an application or an interview.
About SuperAnnotate (SME)
SME Careers matches vetted subject-matter experts to managed AI-training projects, paid weekly.
How it pays: Weekly through Deel as an independent contractor: approved work from Monday to Sunday is paid the following Friday, usually arriving one to three days later. Hourly projects pay tracked active time only.
More AI training jobs for engineers, scientists and software people
An engineer or scientist with deep expertise?
One profile for every employer here. Space companies and their recruiters ask us for people with a specific degree, clearance, specialty or location: add yours once, and when a job fits, we introduce you, only with your yes. Free.
SuperAnnotate (SME) openings, sent to you weekly
Each week we send the newest postings from SuperAnnotate (SME)'s own careers site, along with similar openings at other space employers. It costs nothing and you can stop anytime.