Senior Security Engineer, AI Agent Security

Minimum qualifications:

• 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, network security and security protocols.
• 5 years of experience in coding using 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.
  

Preferred qualifications:

• Experience with agent-based AI systems.
• Experience with API design for large developer audiences, particularly in security domains.
• Proficiency in programming for security research tasks such as scripting, tool development, and data analysis.

About the job

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 a Security Engineer in Information Security Engineering (ISE) Auth, you will contribute to the Secure AI Framework (SAIF) agents program to secure Google's use and development of AI agents. In this role, you have the opportunity for wide influence within Google and across the industry. You will solve open-ended problems and go from initial security research to engineering away classes of problems and addressing their root causes, across the company. You will influence and contribute to the next generation of Google's internal identity and credential systems, such as restricting account credentials to limit the blast radius of rogue agent actions. You will design APIs, processes and tools that not only reduce risk, but also keep developers happy and productive, using the go/safe-coding methodology. You will work with Software Engineers on the team to automate large-scale remediations, harden product frameworks and to build supporting infrastructure for vulnerability research and monitoring. You will work with framework owners (e.g., agency, orcas) and product teams (e.g., jules, bluedog, AI Powered Google (AIPG)) to integrate security controls into their products and to identify the requirements necessary to design the next generation of access control and find solutions that directly benefit AI agents, but also uplift the security posture of Google overall.

The US base salary range for this full-time position is $166,000-$244,000 + bonus + equity + benefits. Our salary ranges are determined by role, level, and location. Within the range, individual pay is determined by work location and additional factors, including job-related skills, experience, and relevant education or training. Your recruiter can share more about the specific salary range for your preferred location during the hiring process.

Responsibilities

• Collaborate with agent platform teams to integrate security principles and establish secure-by-design practices early in the development lifecycle.
• Define, implement, and advocate for secure API design patterns for agent identities, secure interaction and scoped actions.
• Conduct security architecture reviews, threat modeling, and code reviews for agent platforms and related infrastructure, working closely with leads across Privacy Security and Safety (PSS) and product teams to influence and harden agent frameworks.
• Design security controls and features within Google's core AI agent platforms and frameworks (e.g., AIPG, orcas), as well as Google-wide infrastructure (e.g., gaia, apps framework, scaffolding, goa).
• Contribute to secure developer frameworks for AI agent development at Google and help define the next generation of such frameworks.