Test AI systems for vulnerabilities using offensive security techniques and tools.
Attack and defend generative AI architectures, focusing on prompt injection, jailbreaking, and data exfiltration risks. You'll develop Python automation scripts, design protective guardrails, and track emerging AI threats. Works closely with security architects and developers, operating in a fast-moving technical environment. French-speaking role in Paris with hybrid flexibility (2–3 days remote weekly).
Membership is €29/month, cancel anytime: every rate, every original listing link, and a daily alert for roles matching your filters.
Found at a specialist agency · listed 2 September 2026 · InsideJobs links you to the original posting.