Hazardous Device Expert - Red Team

Obsidian; Berlin; Vor Ort; EUR 70.000 - 110.000; Vollzeit

Zusammenfassung

Mercor is assembling a team of public safety and device assessment experts to red-team frontier AI models. You will write prompts across benign, dual-use, and adversarial levels and evaluate model responses against a strict policy standard.

You will also craft reference answers with the underlying technical reasoning and provide written rationales that are understandable to non-specialists. This role emphasizes rigorous writing and clear documentation throughout testing and evaluation.

Qualifikationen

• Public safety professional with device assessment or render-safe experience.
• Red-teaming experience strongly preferred.
• Ability to write clear, structured rationales for non-specialists.

Aufgaben

• Write prompts at benign, dual-use, and adversarial levels.
• Evaluate model responses against a defined policy standard.
• Write the reference answer and the technical reasoning for it.

Kenntnisse

Red-teaming experience

Technical writing

Policy analysis

Ausbildung

Certified bomb technician or hazardous device operator

Tools

Robotics

Disruption tools

Jobbeschreibung

About the work

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, 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.

This domain lives on the dual-use line more than most. The same assessment that tells a technician how to approach a device tells someone else how it was meant to work; the same compatibility data that keeps a magazine safe describes what stays stable elsewhere. A model that refuses a routine storage or render-safe question is failing as badly as one that answers a question it shouldn't. Drawing that line reliably is why we need practitioners rather than generalists.

Background we're looking for

We're looking for public safety professionals who have assessed real devices — the render-safe and post-incident side, held under certification and command accountability. What matters most is being able to tell a routine professional question from one that's fishing for something else: the same assessment that makes a device safe explains how it was built. You will be writing prompts that sit exactly on that line, then judging whether the model held it.

Examples of relevant backgrounds (ideally with red-teaming experience):

• Certified bomb technician or hazardous device operator — device assessment and render-safe procedures


• Military EOD with civilian public-safety, training or instruction experience


• Bomb squad commander or training officer — team qualification, equipment and protocols


• Post-blast investigation and device reconstruction


• CBRNE technical response — standoff assessment, robotics and disruption tools

What this role demands beyond technical depth

This is writing-intensive work. Every judgment you make needs a written rationale that a non-specialist can follow. Prior technical writing, 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 apply

Your 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.