Blasting Engineer & Dual-Use AI Prompts Expert

Mercor; Greater London; On-site; GBP 40,000 - 70,000; Full time

Job summary

Mercor seeks a writer for red-teaming frontier AI models by crafting challenging prompts across benign, dual-use, and adversarial categories. You will evaluate model responses against policy standards and write a reference answer with detailed technical reasoning.

This is a writing-intensive role requiring a clear, documented rationale and sustained work on misuse scenarios in the field. Prior publication or expert-witness experience is a strong signal, with NDA constraints addressed in the

Qualifications

• This role requires writing-intensive work with clear, traceable rationale.
• Prior technical writing, published research, or expert witness experience is a strong signal.
• Ability to read and write about misuse scenarios in your field for sustained periods.

Responsibilities

• Write challenging single-turn prompts in your domain, labeled benign, dual-use, and adversarial.
• Evaluate model responses against a defined policy standard and judge whether each was handled correctly.
• Write the reference answer with the correct response and the technical reasoning.

Job description

Mercor seeks a writer for red-teaming frontier AI models by crafting challenging prompts across benign, dual-use, and adversarial categories. You will evaluate model responses against policy standards and write a reference answer with detailed technical reasoning.

This is a writing-intensive role requiring a clear, documented rationale and sustained work on misuse scenarios in the field. Prior publication or expert-witness experience is a strong signal, with NDA constraints addressed in the