Radiological Safety Red-Teaming Lead

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...

Courbevoie (Paris-La Défense) | Hybride (2j de TT/semaine) | CDIDriver l’intelligence métier et bâtir les agents IA de demain chez le leader de la Fintech.Ici, pas de management. Votre job : accompagnerune équipe tout en gardant les mains dans le code. Dans une squad de 5 Data Scientists, vous concevez, challengez et déployez des architectures...

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...

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...

AI / Emerging Tech Security Analyst (AI Training) About The Role What if your security expertise could directly shape how the world's most advanced AI systems defend against attacks, misuse, and adversarial manipulation? We're looking for AI Security Analysts to put frontier AI models under the microscope — probing their limits, identifying...

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...

Taux journalier (TJM): 600 Opportunité Freelance / Mission Longue Durée Analyste Sécurité Offensive Senior / Lead Télétravail : 3 jours/semaine Démarrage : Asap Durée : 3 ans Dans le cadre du renforcement des activités de cybersécurité offensive, nous recherchons un Analyste Sécurité Offensive expérimenté pour intervenir sur des...

Description de l'entrepriseSia est un groupe international de conseil en management de nouvelle génération, fondé en 1999. Nés à l'ère du digital, nous sommes augmentés par la data, enrichis par la créativité et guidés par la responsabilité. Nous collaborons avec nos clients pour relever les défis et saisir les opportunités. Dans un monde en...