Hybrid LLM Red Team Engineer - Adversarial Security

White Circle is seeking an AI Red Team Engineer to conduct adversarial testing of LLM-powered systems. You will automate attacks, document findings, and support sales with credible evidence.

Ideal candidates should possess strong Python scripting abilities, QA automation experience, and a deep understanding of LLMs and security threats. The role is hybrid, based in Paris, and offers competitive benefits including medical insurance and paid time off.