Explosives & Energetic Materials Expert for AI Safety Audit | Remote - Full Time

Xperteez Technology • ,

11d • Remote

About The Position

Review AI model responses to sensitive questions about explosives and energetic materials. For each task, classify the user request as benign, dual-use, or adversarial; assess each of three model answers for safety and explain the assessment; rank the answers; and provide the response the model should have given. For dual-use requests, identify the sensitive aspects, legitimate purpose, and appropriate audience for an answer. Requests reflect questions from professionals such as mining and blasting engineers, pyrotechnicians, propellant chemists, bomb technicians, and investigators, as well as occasional bad actors. The work includes identifying both dangerous responses and inappropriate refusals of ordinary professional questions.

The role also involves creating prompts and responses for AI training, evaluating and ranking model outputs, and testing models for inaccuracies or bias across use cases. Applicants must be citizens or permanent residents of the United States, United Kingdom, Canada, Australia, New Zealand, or the European Union.

Requirements

• Bachelor’s degree or higher in Chemistry, Chemical Engineering, Materials Science, Energetic Materials, Explosives Engineering, Safety Engineering, Hazardous Materials Management, Environmental Health & Safety, or a closely related field.
• At least 3 years of professional experience in explosives safety, energetic materials, hazardous materials or chemical safety, defense or industrial safety, EHS, regulatory compliance, risk assessment, technical safety review, or related work.
• Strong understanding of explosives and energetic-materials safety concepts, including hazard classification, sensitivity, compatibility, storage, transport, environmental conditions, blast and fire risk, and safe-handling frameworks.
• Familiarity with safety documentation and frameworks such as Safety Data Sheets, GHS hazard communication, hazardous-materials classification, SOPs, risk assessments, incident escalation procedures, and applicable safety or regulatory guidance.
• Ability to review AI-generated explosives or energetic-materials content for technical accuracy, safety alignment, misuse risk, inappropriate specificity, hallucinated claims, and dangerous procedural guidance.
• Ability to distinguish safe high-level educational or safety content from content that could enable unsafe handling, synthesis, acquisition, weaponization, evasion, or harmful experimentation.
• Excellent written English and ability to provide clear, structured feedback explaining whether responses are safe, unsafe, incomplete, misleading, or technically incorrect.
• High attention to detail when reviewing terminology, hazard categories, material properties, units, risk assumptions, safety controls, storage and transport considerations, and emergency-response guidance.
• Comfort applying detailed project rubrics consistently to ambiguous or sensitive scenarios involving explosives, energetic materials, pyrotechnics, propellants, reactive chemicals, or hazardous mixtures.
• Citizenship or permanent residency in the United States, United Kingdom, Canada, Australia, New Zealand, or the European Union.

Nice To Haves

• Advanced degree or professional safety certification.
• Experience writing incident reports, safety cases, or expert opinions.
• Prior experience with AI safety, red-team review, model evaluation, content moderation, data annotation, technical QA, scientific review, EHS review, hazardous-materials review, or rubric-based evaluation.

Responsibilities

• Classify requests as benign, dual-use, or adversarial.
• Assess each AI-generated answer as safe or unsafe and explain why.
• Rank three model answers against one another.
• Write the answer the model should have given.
• For dual-use requests, identify sensitive aspects, legitimate purposes, and who should be able to receive an answer.
• Create detailed prompts and responses across topics to guide AI learning.
• Evaluate and rank AI responses to improve accuracy, fluency, and contextual relevance.
• Test AI models for inaccuracies and biases and validate reliability across use cases.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level