Test Cloud AI systems for vulnerabilities, including jailbreaks, data exfiltration, prompt injections, and adversarial manipulation. Uncover novel vulnerabilities across new and complex AI features. Build and calibrate anti-abuse detection systems and AI agents to protect Cloud and Workspace products at scale. Investigate and remediate abuse incidents while using findings to refine detection agent performance. Review and develop secure operational practices, and provide security guidance for engineers and analysts.
Job description provided by Google.
View the original posting
