Senior Security Engineer, Serving Layer and Platform Security, DeepMind at Google in Mountain View, CA, USA

Job description

• There's no such thing as a "safe system"—only safer systems. The GDM Product Security Team serves as the single point of accountability for GDM's product security posture by providing embedded, specialized security expertise across infrastructure and product development lifecycles, from early design through production operations. The team ensures GDM’s products and systems remain a secure and reliable frontier AI platform by bridging product development with Google's horizontal security functions and the GDM Security and Privacy organization.
• In this role, you will focus on securing GDM’s core serving infrastructure and underlying platform layer (including Beyond, Agency, AI Studio / GeminiAPI, and TPU inference systems). You will proactively evaluate and harden serving components, enforce multi-tenancy data protection, design OS/hardware workload isolation, and build secure-by-default paved paths for model serving. Because operational security is core to maintaining our frontier AI platform, this position requires a direct background in security operations, including vulnerability triage, threat modeling, incident escalation, and rotational on-call support.
• Artificial intelligence will be one of humanity’s most transformative inventions. At Google DeepMind, we are a pioneering AI lab with exceptional interdisciplinary teams focused on advancing AI development to solve complex global challenges and accelerate high-quality product innovation for billions of users. We use our technologies for widespread public benefit and scientific discovery, ensuring safety and ethics are always our highest priority.
• We are pushing the boundaries across multiple domains. Our global teams offer diverse learning opportunities and varied career pathways for those driven to achieve exceptional results through collective effort.

Responsibilities

• Evaluate and harden GDM’s core serving infrastructure (Beyond, Agency, AI Studio APIs) and inference pipelines.
• Develop and maintain threat models covering GDM serving layers and inference workloads. Model attack vectors unique to frontier AI, including prompt injection mitigation, tool-calling hardening, multi-tenant data boundary protection, and API surface security.
• Build secure-by-default libraries, reference architectures, and deployment templates that embed infrastructure security into GDM’s deployment pipelines and serving stacks.
• Participate in the team's operational security rotation (on-call).

Requirements

• Bachelor's degree in Computer Science, Cybersecurity, Electrical/Computer Engineering, or equivalent practical experience.
• 5 years of experience in security engineering, platform security, infrastructure hardening, network protocols, or systems security architecture.
• 5 years of experience in security operations (e.g., operational security monitoring, incident response, vulnerability triage, rotational on-call duty, or threat hunting).
• 5 years of coding experience in one or more systems programming languages (e.g., C, C++).
• Experience securing large-scale distributed serving infrastructure, core API development, multi-tenant data architectures, etc.
• Demonstrated experience conducting variant analysis, developing security mitigations, and responding to high-severity infrastructure incidents in a production environment.
• Expertise in workload isolation, Linux kernel security, TPU/GPU architecture security, or hardware-backed root-of-trust models.
• Technical understanding of frontier AI security challenges, including prompt injection containment, secure agentic tool execution, and inference memory safety.

Skills

Required

• Security engineering
• Platform security
• Infrastructure hardening
• Network protocols
• Systems security architecture

Preferred

• Core API development
• Multi-tenant data architectures
• Variant analysis
• Developing security mitigations
• Workload isolation
• Linux kernel security
• TPU/GPU architecture security
• Hardware-backed root-of-trust models

Benefits

• Individual pay is determined by factors including job-related skills, experience, and relevant education or training.
• US: $207000 - $300000 (USD) + 20% bonus target + equity + benefits
• Learn more about benefits at Google.