Senior Security Engineer – Frontier AI Platform Security

Google DeepMind; New York (NY); On-site; USD 207,000 - 300,000; Full time

Job summary

Google DeepMind is seeking a product security engineer to reinforce the security of its core serving infrastructure and platform layers. You will develop threat models for multi-tenant inference workloads, implement secure-by-default patterns, and contribute to secure deployment templates across the GDM stack.

The role emphasizes hands-on security operations, vulnerability triage, and incident response in a frontier AI environment, collaborating with cross‑functional teams to maintain a safe,

Qualifications

• Bachelor's degree or equivalent practical experience in CS, cybersecurity, or related field.
• 5 years in security engineering, platform security, or infrastructure hardening.
• 5 years in security operations (monitoring, incident response, vulnerability triage, on-call, threat hunting).
• 5 years of coding experience in systems languages (e.g., C, C++).

Responsibilities

• Evaluate and harden core serving infrastructure (Beyond, Agency, AI Studio APIs).
• Develop threat models for serving layers and inference workloads; address prompt injection and multi-tenant data boundaries.
• Build secure-by-default libraries, architectures, and deployment templates for pipelines and stacks.
• Participate in the security rotation (on-call) and incident response practices.

Skills

Security engineering

Security operations

Systems programming

C/C++ coding

Education

Bachelor's degree in CS/EE or equivalent

Job description

Google DeepMind is seeking a product security engineer to reinforce the security of its core serving infrastructure and platform layers. You will develop threat models for multi-tenant inference workloads, implement secure-by-default patterns, and contribute to secure deployment templates across the GDM stack.

The role emphasizes hands-on security operations, vulnerability triage, and incident response in a frontier AI environment, collaborating with cross‑functional teams to maintain a safe,