Public Safety Red Team Specialist

Mercor; San Francisco (CA); Remote; USD 120,000 - 180,000; Full time

Job summary

Mercor is assembling a panel of energetic materials and propulsion 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 prompts across benign, dual-use, and adversarial categories, and evaluate responses against a defined policy standard.

Qualifications

• Backgrounds with red-teaming experience preferred.
• Strong written rationale for every judgment.
• Public safety professionals with device assessment background are valued.

Responsibilities

• Write challenging prompts across benign, dual-use, and adversarial levels.
• Evaluate model responses against a defined policy standard.
• Write the reference answer with technical reasoning for why it is correct.

Skills

Red-teaming experience

Technical writing

Policy reasoning

Education

Certified bomb technician

EOD background

Bomb squad commander

Post-blast investigation

CBRNE technical response

Job description

Mercor is assembling a panel of energetic materials and propulsion 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 prompts across benign, dual-use, and adversarial categories, and evaluate responses against a defined policy standard.