AI Security Engineer

Role & responsibilities

Job Description

Job Title: AI Security Engineer GSD Security Team Overview: As an AI Security Engineer, you wil be responsible for securing the end-to-end AI and machine learning lifecycle. Your role is critical in protecting AI infrastructure, ensuring data privacy for training sets, and defending against adversarial ML threats. You wil lead the integration of security controls into model development and deployment, with a strong focus on securing generative AI services and enterprise agentic AI workflows using Gemini Enterprise and Google Cloud's AI security suite. In this role, you wil provide expert architectural guidance to help customers build, deploy, and maintain highly resilient, secure AI environments. Responsibilities: Secure AI/ML Pipelines: Design and implement robust security controls for AI/ML pipelines, ensuring the integrity and confidentiality of models and data from ingestion to deployment. Gemini Enterprise Security & Governance: Define, configure, and audit enterprise security baselines for Gemini Enterprise, focusing on data privacy, cloud data loss prevention (DLP), access controls, and administrative policies to prevent unauthorized data exposure. Threat Modeling & Assessment: Conduct threat modeling and specialized security assessments targeting AI infrastructure and large language models (LLMs), covering risks such as model theft, data poisoning, prompt injection, and unauthorized data egress. Adversarial Defenses: Colaborate with data science and engineering teams to operationalize adversarial ML defenses, secure agentic architectures (Agent Gateway/Registry), and deploy privacy-preserving techniques. Security Operations & Telemetry: Develop strategies for monitoring AI-specific security telemetry and integrating logs from Vertex AI and Gemini Enterprise into Security Command Center Enterprise (SCC-P). Technical Enablement: Deliver technical workshops and training on secure AI development practices to customer stakeholders. Minimum Qualifications: Strong background in security engineering with specialized experience in AI/ML security, including model protection and adversarial machine learning. Proven experience securing AI infrastructure and cloud-native services on platforms like Google Cloud (Vertex AI, GKE, etc.). Deep understanding of data privacy regulations and technical implementations for securing large-scale training datasets. Ability to conduct technical security workshops and communicate complex AI risks to both technical and non-technical stakeholders. Preferred Qualifications: Google Cloud Professional Machine Learning Engineer or Professional Security Engineer certification. Experience with AI security frameworks and performing AI-specific red teaming or audits. Familiarity with securing Generative AI and Large Language Models (LLMs) in production environments