Senior Security Engineer, AI Protection

Google•Seattle, WA

About The Position

Our Security team works to create and maintain the safest operating environment for Google's users and developers. Security Engineers work with network equipment and actively monitor our systems for attacks and intrusions. In this role, you will also work with software engineers to proactively identify and fix security flaws and vulnerabilities. As the Senior Security Engineer, you will utilize your security engineering expertise to combat novel Generative AI (GenAI) threats and provide technical leadership in cybersecurity, intelligence, and threat analysis. You will lead efforts to secure AI products and agents against sophisticated and novel attacks. You will be building protection and intelligence for Gen AI Application Programming Interface (API) Abuse and Security, ensuring the reliability and security of Cloud and Workspace AI systems. You will mentor the engineers and analysts, partner closely with AI researchers, and drive cross-functional security initiatives that shape the future of secure AI at Google Cloud scale.

Requirements

Bachelor's degree or equivalent practical experience.
5 years of experience with security assessments or security design reviews or threat modeling.
5 years of experience with security engineering, computer and network security and security protocols.
5 years of coding experience in one or more general purpose languages.
1 year of experience leading teams in a technical capacity or leading technical risk analysis in an enterprise environment.

Nice To Haves

Experience in applied vulnerability research, or advanced pen testing/red teaming.
Experience in conducting AI Red Teaming or participating in AI bug bounties.
Experience in analyzing systems and identifying security and abuse problems, threat modeling, and remediation.
Understanding of Generative AI technologies, Large Language Models (LLMs), and AI agents.

Responsibilities

Drive the direction for Cloud AI security initiatives, architect comprehensive threat models for AI ecosystems, and mentor teams on secure operational practices.
Identify and analyze novel attack vectors targeting AI agents and underlying Large Language Models (LLMs), including advanced reasoning manipulation, data exfiltration, and model inversion.
Lead advanced adversarial simulations and assessment of Cloud AI systems, architecting novel testing frameworks to expose multi-stage vulnerabilities.
Pioneer vulnerability research methodologies and establish continuous discovery programs to systematically expose zero-days and unknown attack vectors across next-generation Cloud AI products.
Direct the rapid investigation and mitigation of high-severity AI abuse incidents, collaborating across product and research teams to deploy enterprise-wide security improvements.