Radiological Safety Red-Teamer & Prompt Architect

Obsidian; Toronto; Remote; CAD 90,000 - 130,000; Full time

Job summary

Mercor is assembling a panel of radiological safety experts to red-team frontier AI models, testing whether a model can judge misuse potential while answering legitimate questions. You will write challenging prompts across benign, dual-use, and adversarial levels, evaluate model responses against a policy standard, and craft reference answers with technical reasoning.

The role emphasizes written rationale and sustained analysis of misuse scenarios, with prior technical writing or expert witness

Qualifications

• Candidates have red-teaming or security assessment experience with licensed materials or sensitive domains.
• Strong ability to write clear, structured rationales for technical assessments.
• Experience with policy-based evaluation of AI model outputs is a plus.

Responsibilities

• Write prompts across benign, dual-use, and adversarial categories.
• Evaluate model outputs against a defined policy standard.
• Draft reference answers with technical reasoning.

Skills

Red-team experience

Technical writing

Policy analysis

Domain knowledge

Job description

Mercor is assembling a panel of radiological safety experts to red-team frontier AI models, testing whether a model can judge misuse potential while answering legitimate questions. You will write challenging prompts across benign, dual-use, and adversarial levels, evaluate model responses against a policy standard, and craft reference answers with technical reasoning.

The role emphasizes written rationale and sustained analysis of misuse scenarios, with prior technical writing or expert witness