Senior Security Engineer, Serving Layer and Platform Security

DeepMind is hiring a Senior Security Engineer to strengthen the security of its serving layer and underlying platform infrastructure, including inference systems.

Responsibilities

• Assess and harden GDM core serving infrastructure, including Beyond, Agency, AI Studio APIs, and the associated inference pipelines
• Create and maintain threat models for GDM serving layers and inference workloads
• Cover frontier-AI-specific attack vectors, including:
  • Prompt injection mitigation
  • Tool-calling hardening
  • Multi-tenant data boundary protection
  • API surface security
• Develop and maintain secure-by-default libraries, reference architectures, and deployment templates that embed infrastructure security into GDM deployment pipelines and serving stacks
• Participate in the team operational security rotation and support on-call duties

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, such as:
  • Operational security monitoring
  • Incident response
  • Vulnerability triage
  • Rotational on-call duty
  • Threat hunting
• 5+ years of coding experience in one or more systems programming languages (e.g., C, C++)

Technology

• C
• C++

Preferred Qualifications

• Experience securing large-scale distributed serving infrastructure, core API development, multi-tenant data architectures, and related areas
• Demonstrated experience performing variant analysis, building security mitigations, and responding to high-severity infrastructure incidents in production
• 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
  • Inference memory safety

Compensation

• US Salary: $207,000 - $300,000 (USD) per year
• Bonus target: 20%
• Equity
• Benefits

Location

• Mountain View, CA, USA (hybrid)
• New York, NY, USA (hybrid)

Team Scope

• The GDM Product Security Team serves as the single point of accountability for GDM product security posture
• Provides embedded, specialized security expertise across infrastructure and product development lifecycles, from early design through production operations
• Focus in this role includes securing the core serving infrastructure and underlying platform layer, including:
  • Beyond
  • Agency
  • AI Studio / GeminiAPI
  • TPU inference systems

Note: Learn more about benefits at Google.