Licensed Blasting & AI Safety Red Team Engineer

Mercor; San Francisco (CA); On-site; 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 single-turn prompts in your domain, label across three levels: benign, dual-use, and adversarial; evaluate the responses that come back against a defined policy standard, and judge

Qualifications

• This is a writing-intensive role requiring clear, structured rationales for each judgment.
• Candidates with prior technical writing, published research, or expert witness experience are preferred; include samples or links.
• You will read and write about misuse scenarios in your field for extended periods.

Responsibilities

• Write challenging single-turn prompts labeled benign, dual-use, and adversarial.
• Evaluate model responses against a defined policy standard.
• Write the reference answer and the technical reasoning explaining why a response is correct.

Skills

Red teaming

Technical writing

Prompt engineering

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 single-turn prompts in your domain, label across three levels: benign, dual-use, and adversarial; evaluate the responses that come back against a defined policy standard, and judge