Security Engineer at Google

Compensation

$207,000 – $300,000/yr

Location: Mountain View, California · New York, New York
Type: Full-time
Level: senior
Posted: Sep 17, 2026

Description

Google DeepMind is hiring a Security Engineer to secure its core serving infrastructure and underlying platform layer, including Beyond, Agency, AI Studio APIs, and TPU inference systems. The role focuses on hardening serving components, developing threat models, protecting multi-tenant data, designing workload isolation, and building secure-by-default deployment templates. It also requires participation in operational security rotation and on-call support. The position requires a relevant bachelor's degree or equivalent practical experience, five years of security engineering or security operations experience, and five years of systems programming experience.

Required Skills

Security operations
Threat modeling
Vulnerability triage
Workload isolation
Systems programming
Linux kernel security
TPU/GPU security

Additional Information

Minimum Education: Bachelor's degree in Computer Science, Cybersecurity, Electrical/Computer Engineering, or equivalent practical experience
Required Previous Experiences: 5 years of experience in security engineering, platform security, infrastructure hardening, network protocols, or systems security architecture
5 years of experience in security operations, including monitoring, incident response, vulnerability triage, on-call duty, or threat hunting
5 years of coding experience in one or more systems programming languages, such as C or C++
Preferred Qualifications: Experience securing large-scale distributed serving infrastructure, core API development, and multi-tenant data architectures
Experience conducting variant analysis, developing security mitigations, and responding to high-severity production infrastructure incidents
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