Analytical Chemist - Hazardous Compounds

Mercor; Berlin; Vor Ort; EUR 70.000 - 90.000; Vollzeit

Zusammenfassung

Mercor seeks analysts to assemble a panel for red-teaming frontier AI models, focusing on misuse potential of technical requests. You will craft prompts, evaluate model responses, and develop reference answers with clear justification.

The role emphasizes writing-intensive work, with the ability to explain complex judgments to non-specialists. Prior published work or expert testimony is a strong signal; flexibility and sustained reading/writing on misuse scenarios are valued.

Qualifikationen

• Ability to write a clear rationale accessible to non-specialists.
• Experience in distinguishing routine questions from misuse signals in scientific domains.
• Strong background in hazardous compounds detection and identification.

Aufgaben

• Write challenging prompts across benign, dual-use, and adversarial levels.
• Evaluate model responses against a policy standard.
• Write reference answers and provide technical reasoning.

Kenntnisse

Red-teaming experience

Technical writing

Judgement under scrutiny

Tools

GC-MS

LC-MS/MS

IR

NMR

Jobbeschreibung

About the work

Mercor is assembling a panel of chemistry and chemical safety 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 method that detects a hazardous compound at trace level defines the threshold someone would try to stay beneath; the same library entry that identifies an unknown tells you what a screen will and won't see. A model that refuses a routine method‑validation 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 analysts who have built and validated methods for hazardous compounds — people who know what a detection limit really means and what it implies. What matters most is being able to tell a routine professional question from one that's fishing for something else: the same detection method that finds a compound describes how to evade the screen. 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):

• Detection and identification of hazardous compounds — GC-MS, LC-MS/MS, IR, NMR
• Method development and validation for trace-level analysis
• Environmental, occupational or emergency‑response sampling and analysis
• Reference standards, spectral libraries and unknown identification
• Laboratory accreditation, QA/QC and proficiency testing

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.