Senior Security Engineer, Trust and Safety, Intel Security Engineering

Google•Washington, DC

2d•$174,000 - $252,000

About The Position

The Senior Security Engineer, Trust and Safety (T&S) Intel Security Engineering leads Detection and Response for severe generative AI-related security incidents affecting third-party users, customers, and the general public. The role serves as a subject matter expert in AI Security and builds cross-Google relationships to support risk transparency and effective prioritization, mitigation, and resolution of AI security risks. Outside active incidents, the engineer improves Detection and Response readiness by building and maintaining playbooks and escalation processes, ensuring appropriate detection coverage, and exercising incident management processes through tabletop exercises. The role also supports T&S's Operational Intelligence lifecycle for AI security issues, focusing on emerging cybersecurity and frontier AI risks. This includes designing or developing tools and pipelines to surface risk signals and driving their detection, enrichment, and analysis to deliver actionable intelligence to internal stakeholders.

Requirements

Bachelor's degree or equivalent practical experience.
5 years of experience with security assessments, security design reviews, or threat modeling.
5 years of experience with security engineering, computer and network security, and security protocols.
5 years of coding experience in one or more general-purpose languages.
1 year of experience leading teams in a technical capacity or leading technical risk analysis in an enterprise environment.

Nice To Haves

Experience working with product teams to remediate identified issues.
Experience working with external parties or in a publicly-facing role.
Experience with generative AI or similar AI/ML systems.

Responsibilities

Drive T&S Intel's Detection and Response functions, including pre-incident preparedness, cross-Google relationship development, playbooks, escalation procedures, and process improvement.
Support urgent detection and response for critical AI security issues affecting external users, developers, and the general public, including on-call incident management during business hours.
Provide security subject-matter expertise to T&S Intel.
Develop tools, processes, and signal sources supporting detection, enrichment, and analysis of security-related issues, especially risks related to GenAI products.
Inform and mobilize decision makers and other stakeholders to catalyze systemic risk mitigation and enhance transparency.
Assess the validity and severity of externally and internally discovered AI security and abuse issues; reproduce and validate reports and capture information product teams need to understand and resolve issues.
Design or develop tools and pipelines to surface risk signals, and drive detection, enrichment, and analysis of those signals for actionable intelligence.