AI Security Researcher: Adversarial ML & High Assurance

CommonAI CIC in Cambridge is seeking an AI Security Researcher with an attacker mindset to challenge how AI systems can be broken, misused or circumvented. You will support the High Assurance programme, focusing on accuracy, explainability and accountability of AI in regulated environments such as financial services.

You will track research, test attacks, threat-model systems, and help develop interpretable models while sharing findings with Members.

#J-18808-Ljbffr…