Principal Engineer, Safeguards

Google•Sunnyvale, CA

3d•$307,000 - $427,000

About The Position

Within Google Cloud’s Cloud AI organization, the Principal Engineer, Cloud AI Safeguards is a senior individual contributor and the technical authority for safety and security across the Cloud AI product portfolio, with a primary focus on agentic safety. The role sets technical direction without managing people by defining architecture, raising engineering standards, and personally designing and building defenses that meaningfully reduce risk as model capabilities, product surfaces, and adversaries evolve. Agentic systems create more complex safety challenges because autonomous tool use, long-horizon planning, and untrusted inputs expand the attack surface. This role is responsible for anticipating that complexity and developing safeguards for agentic systems. The ideal applicant investigates difficult problems with curiosity and objectivity, works across teams to recommend solutions, and makes complexity understandable through clear explanations and thoughtful design. Cloud AI builds scalable products and services, including Vertex AI and Gemini Enterprise, for developers, data scientists, and operations specialists across industries. Its portfolio includes state-of-the-art models, agent platforms, and applications with security and governance capabilities.

Requirements

Bachelor’s degree in Computer Science or equivalent practical experience.
15 years of professional experience in engineering leadership or related technical roles.
Experience in AI and machine learning, including building and deploying classifiers and ML systems in production.

Nice To Haves

Command of threat modeling, particularly for complex, evolving, and adversarial systems.
Experience securing agentic or autonomous AI systems, including tool use, planning, and multi-agent systems.
Experience with agent platform technologies such as Vertex AI or Gemini Enterprise.
Demonstrated ability to make risk-based trade-offs and reduce complexity in difficult problem spaces.
A proven track record of building defenses that have meaningfully and measurably reduced risk.
Depth in adversarial ML, red-teaming, or abuse/fraud detection.
A strong track record of influencing without authority and working effectively across teams.

Responsibilities

Design, prototype, and ship safeguards for AI-driven threats across CBRN, cyber, agentic, and fraud risks using classifiers, runtime policy enforcement, and ML systems.
Own the technical vision and reference architecture for safeguarding agentic systems across tool use, planning, memory, and multi-agent interactions.
Lead threat modeling for increasingly complex attack surfaces, anticipate adversary behavior, and translate findings into concrete engineering requirements and defenses.
Shape shared safety and security infrastructure for AI workloads and ensure defenses are reusable across products.
Work objectively across teams to diagnose problems, recommend solutions, align on standards, and raise the engineering bar through design reviews and mentorship.
Build data analysis, detection, and response capabilities to observe safety-relevant behavior at scale, measure efficacy, and respond quickly to emerging threats.