Design AI Security architecture and validation frameworks for agentic platforms, connecting local solutions to central security standards.

Design security architecture and validation frameworks for agentic platforms, including prompt injection resilience and data flow constraints (e.g., agentic access and vulnerability systems).
Define technical standards and automated workflows for vulnerability auto-mitigation aligned with global SLO timelines.
Architect automated access control systems, integration templates, and data flow constraints to help prevent access abuse and data exfiltration.
Develop holistic mapping of agentic threat models to engineering solutions for preventing and detecting material risks before they manifest.
Align all technical architectures with central security design standards and act as a primary design conduit to central infrastructure.
Provide precise technical designs for the Operational Engineering (Build) team to support software fulfillment.

Bachelor’s degree in Computer Science, Cybersecurity, a related technical field, or equivalent practical experience.
2+ years of experience in security engineering, threat modeling, systems design, or security architecture.
Experience coding for security-relevant software in C++, Java, Go, or Python.
Master’s degree or PhD in Computer Science or a related technical field.
Experience designing security controls for large-scale distributed systems or cloud infrastructure.
Experience architecting enterprise-scale security tools, access control systems, or observability platforms.
Deep technical understanding of LLMs and AI security risks including prompt injection and data poisoning, plus deploying deterministic security harnesses.
Strong ability to influence executive engineering partners on critical design decisions.

gTech Risk helps protect Google and its users by identifying and implementing controls for significant risks.
gTech Risk Solutions Engineering is evolving from a reactive, manual process to a proactive engineering organization.
Within the AI Security function, you will support the core experts of the Functional Engineering pod (Strategy and Design).
You will own overarching system design for autonomous risk identification, AI guardrails, and vulnerability auto-mitigation.
A key focus is architecting security constraints for gTech’s current and future operations.
You will design validation frameworks, including prompt injection resilience, for agentic platforms deployed on global configurations.
You will serve as a bridge to central teams, ensuring local solutions conform to Google’s general security policies while supporting the pace of gTech operations.

AI Solution Security Engineer

Job Description