In this role, you will play a vital role in ensuring that Google Cloud’s Artificial Intelligence (AI) products are not only powerful but also safe, secure, and trustworthy. Your investigative skills, understanding of potential security harms, for user protection will help the teams solve testing problems in AI security and abuse at scale. You will proactively identify and mitigate emerging threats within the AI landscape, ranging from adversarial attacks to potential misuse of generative technologies. You will synthesize large datasets to uncover patterns of abuse, ensuring that Google's AI deployments remain resilient against sophisticated exploitation while upholding our responsibility for safe AI growth.

Develop and deploy scalable safety solutions for Cloud AI products by leveraging advanced machine learning and AI techniques.

Use data analysis to discover and interpret how attackers exploit Cloud AI infrastructure or use Application Programming Interfaces (APIs) for abuse, identifying weak points in our systems.

Define what constitutes abuse in ambiguous or highly novel AI use cases, ensuring our guidelines adapt to AI-driven attacks.

Analyze and measure generative/agentic AI risks using benchmarking, dataset design, and scaled usage monitoring.

Drive the rapid response for high-priority AI security incidents, conducting through Root Cause Analyses (RCAs) to implement sustainable long-term solutions. Partner with Engineering and Product teams to identify, prioritize, and develop strategies against the most pressing and novel AI threats.