Security Engineer, AI Protection

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 the Trust and Safety security engineer, you are a thought leader and subject matter expert in AI safety and security. You are responsible for identifying emerging patterns and trends across a full-spectrum of threats and translating the findings into actionable insights and protections. With your knowledge and passion for learning new things, you will help the teams to solve the classes of challenging problems in AI security and misuse at Google scale. You will be essential in building robust protection and intelligence for Gen AI API Abuse and Security, ensuring the reliability, robustness, and security of Cloud and Workspace AI systems including agents.

US: $147000 - $210000 (USD) + 15% bonus target + equity + benefits

Learn more about benefits at Google.

Responsibilities

• 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.

Qualifications

Minimum qualifications:

• Bachelor's degree or equivalent practical experience.
• 2 years of experience with security assessments or security design reviews or threat modeling.
• 2 years of experience with security engineering, computer and network security and security protocols.
• 2 years of coding experience in one or more general purpose languages.

Preferred qualifications:

• Experience 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.