AI Security Researcher: Red Teaming for High-Assurance AI

CommonAI CIC in Australia seeks an AI Security Researcher with an attacker mindset to probe, break and improve AI systems used in regulated environments. You will track research for the High Assurance programme, challenge technical decisions, and test whether simpler, interpretable models are easier to audit.

You will red-team, threat-model, develop interpretability methods, and share findings with Members. Strong Python and publishing clear briefings are essential.