Chemical Safety Red-Teaming Strategist

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 prompts, evaluate the responses that come back against a...

Mercor in Paris seeks a senior technical writer to craft challenging prompts across benign, dual-use, and adversarial categories for frontier AI model red-teaming. You will evaluate model outputs against policy standards, draft reference answers with technical justification, and translate complex safety considerations into clear guidance.This role blends...

About the workMercor 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

Mercor is assembling a panel of radiological safety experts to red-team frontier AI models. You will craft prompts across benign, dual-use, and adversarial levels, then evaluate model responses against a defined policy.You will also write the reference answers and the technical reasoning for why a response is correct or not. This role emphasizes...

About the workMercor is assembling a panel of radiological 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 while answering legitimate questions fully while refusing genuinely dangerous ones.You

TL;DR: We're looking for a research scientist to build autonomous, large-scale environments that push LLM agents (single and multi-agent) to failure, and study how they actually break.About usWhite Circle is an AI Safety company building the safety, reliability, and optimization layer for AI systems. At the core of our platform are policies – simple...

About the work Mercor is assembling a panel of nuclear materials and safeguards 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...

Mercor is building a panel of chemistry and chemical safety experts to red-team frontier AI models. You will craft prompts across benign, dual-use, and adversarial categories, then evaluate model responses against a policy standard.The role requires clear written rationale for every judgment, with sample references and links. Strong background in hazardous...

TL;DR: We're looking for a research engineer to build and maintain our internal suite of benchmarks, covering single/multi-turn content and agentic guardrails. The research engineer would also work with the team on projects studying agent behaviours in the wild.About usWhite Circle is an AI Safety company building the safety, reliability, and optimization...