• Contribute to the development of paths for AI use within Alphabet by validating existing advice and guidelines, identifying gaps, and proposing improvements in collaboration with security engineering partners.

• Propose and validate prevention capabilities to significantly reduce the risk of first-party and third-party agentic AI use, such as ensuring policy adherence and preventing execution of risky actions, by working with security risk leads responsible for reducing Google’s top cybersecurity risks.

• Drive decisive containment and remediation when high-risk or unauthorized agentic AI use is identified, including suspending rogue agents and executing ongoing remediation tasks.

• Partner with adjacent enterprise security teams, such as detection and response, identity, access, and endpoints, to ensure cohesive strategies for reducing risk from agentic AI use.

Google will be prioritizing applicants who have a current right to work in Singapore, and do not require Google's sponsorship of a visa.

• Bachelor's degree or equivalent practical experience.

• 8 years of coding experience in one or more general purpose languages (e.g., Python, C, C++, Java, Go).

• 8 years of experience with security engineering, computer and network security and security protocols.

• 5 years of experience with security leading teams in a technical capacity or leading technical risk analysis in an enterprise environment.