Quick Overview
Job Description
Mercor is assembling a panel of explosives and energetic materials experts to red-team frontier AI models. The goal is to test whether a model can correctly judge the misuse potential of a technical request: Answering legitimate questions fully while refusing genuinely dangerous ones.
You will:- Write challenging single-turn prompts in your domain, labelled across three levels: benign, dual-use, and adversarial.
- Evaluate the responses that come back against a defined policy standard, and judge whether each was handled correctly.
- Write the reference answer; what a correct response looks like, and the technical reasoning for why.
Models tend to fail this domain in both directions: refusing routine questions a mining engineer or investigator asks daily, then engaging with a request they should have shut down because it arrived in academic clothing. Knowing which is which takes someone who has done the work.
Background we're looking forWe're recruiting across two profiles and need both: chemists with specialty materials expertise, and engineers or operators with initiation and propulsion system experience. Prior AI evaluation or red-teaming experience is preferred. Relevant backgrounds include:
- Hazardous Device Specialist / Public Safety Professional - render-safe procedures and device assessment.
- Specialty Materials Chemist (pyrotechnics or propulsion) - formulation, synthesis and performance testing.
- Federal Certified Materials Specialist / Incident Analyst - forensic identification and scene analysis.
- Propulsion & Effects Engineer - munitions and propulsion system design.
- Commercial Blasting Engineer - specialty materials handling, storage and transport.
This is writing-intensive work. Every judgment you make needs a written rationale that a non-specialist can follow. Prior technical writing, incident or post-blast reporting, published research, or expert witness experience is a strong signal; please include a sample or link.
You will also be reading and writing about misuse scenarios in your field for sustained periods. We brief experts on this in advance, and you can pause or step away at any point without penalty.
Before you applyYour work here will not involve, and must not draw on, classified or export-controlled information, or anything covered by an NDA or prepublication review obligation. If you hold such obligations you may still be a good fit; tell us in your application and we will scope the work accordingly.
Similar jobs
- PA
Technology Lead - Digital Workplace
NewPerth Airport Pty Ltd
Alpha, Queensland🇦🇺On-site1 hour agoBudgetingComplianceGenerative AI+1 - TE
Product Engineering Lead, Keet (100% Remote, Worldwide)
NewTether
Brisbane, Queensland🇦🇺Remote1 hour agoEncryptionBlockchainJavaScript+1 - CO
Senior APAC FX Solutions Strategist
NewCorpay
Sydney🇦🇺Hybrid1 hour agoDerivatives - NY
Senior Product Engineer
NewNYLON
Sydney🇦🇺Hybrid1 hour agoDockerNode.jsAWS+7 - ME
AI Research Scientist - PhD
NewMercor
Sydney🇦🇺A$55 - A$90/hrHybrid1 hour agoOnboarding - SM
Senior Environment Manager
NewSmartRecruiters, Inc.
Sydney🇦🇺Hybrid1 hour agoComplianceMental HealthRisk Management - PA
Technology Lead - Enterprise Applications
NewPerth Airport Pty Ltd
Alpha, Queensland🇦🇺Hybrid1 hour agoContinuous Improvement - RB
Hybrid Integration Specialist: Secure, High Availability
NewReserve Bank of Australia
Sydney🇦🇺Hybrid1 hour ago - OC
First Nations Culture & Inclusion Lead - Hybrid
NewOurmob.com.au Chemistry Pty
Sydney🇦🇺Hybrid1 hour agoReconciliation - AA
Safety & Quality Partner
NewAirbus Australia
Brisbane, Queensland🇦🇺On-site1 hour agoComplianceContinuous ImprovementRegulatory Compliance+3 - CO
Senior FX Solutions Specialist
NewCorpay
Melbourne, Victoria🇦🇺Hybrid1 hour agoComplianceDerivativesRisk Management+1 - PA
Tech Lead, Digital Workplace & AI Automation
NewPerth Airport Pty Ltd
Alpha, Queensland🇦🇺Hybrid1 hour ago