AI Security Engineer

As an AI Security Engineer, you will 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 will work to integrate security into model development and deployment, providing expert guidance to help customers build and maintain resilient, secure AI environments on Google Cloud. Responsibilities: ● Design and implement security controls for AI/ML pipelines, ensuring the integrity and confidentiality of models and data from ingestion to deployment. ● Conduct threat modeling and security assessments specifically targeting AI infrastructure, including model theft, data poisoning, and prompt injection attacks. ● Collaborate with data science and engineering teams to operationalize adversarial ML defenses and implement privacy-preserving techniques like differential privacy. ● Develop and deliver training on secure AI development practices and leading strategies for monitoring AI-specific security telemetry in Security Command Center Enterprise (SCCE). 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 ● GCP Security \& Compliance: Expertise in Google Cloud Platform (GCP) landing zone security, compliance, and framework governance. ● Data Loss Prevention (DLP) \& Responsible AI: Knowledge of responsible AI strategies and configuring DLP capabilities, specifically leveraging Model Armor. ● Secure Architecture \& Perimeter Controls: Ability to design secure GCP architectures and implement foundational networking and Virtual Private Cloud Service Controls (VPC SC) to prevent data exfiltration. ● Identity \& Access Management (IAM): Skill in creating sample IAM policies and configuring role-based permissions to enforce controlled agent sharing. ● Security Logging \& Audit Tracking: Proficiency in setting up log sinks, tracking Gemini Enterprise usage audit logs, and writing specific log queries for enterprise-wide visibility. ● Security Tool Integration: Ability to integrate GCP log sinks into existing security tools like Microsoft Sentinel or Defender, including configuring dashboards and alerting. ● Authentication Flow Configuration: Skills to configure and validate Microsoft Entra ID integration to establish a secure authentication flow. ● Cloud Capability Specialization: Deep certified technical expertise focusing on cloud capability specialties such as networking, infrastructure, and security.