GenAI Senior Security Engineer, Red Team

Google•Washington, DC

2h•$174,000 - $252,000

About The Position

As a Generative AI Senior Security Engineer on the Content Adversarial Red Team (CART), part of a broader cross-team effort focused on frontier safety, you will lead offensive cyber misuse red teaming across Google’s Frontier Generative AI products. You will design and execute sophisticated adversarial evaluations covering multi-stage cyber kill chains, exploit and malware generation, security control bypasses, and indirect prompt injection. Working with cross-functional stakeholders and Responsible AI (RAI) Testing teams, you will translate test results into reports and findings that help protect users and potential targets of cyber misuse attacks. Google’s Security team works to create and maintain a safe operating environment for users and developers. Security Engineers work with network equipment, monitor systems for attacks and intrusions, and partner with software engineers to proactively identify and fix security flaws and vulnerabilities. The role involves reviewing graphic, controversial, and offensive content in line with Google’s user policies. It may occasionally require extended hours, including nights or weekends.

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 with offensive security and red-team operations, including exploit or malware analysis, vulnerability research, or bug bounty programs (VRPs).
Experience evaluating or stress-testing Generative AI models, LLM agents, or AI/ML systems, including prompt injection, jailbreaking techniques, sandbox escapes, and AI safety principles.
Experience writing Python code in production or testing environments to automate security assessments, develop testing harnesses, or build exploit proof-of-concepts.
Background in threat intelligence, anti-abuse engineering, or cyber kill-chain analysis, including analyzing emerging threat landscapes and developing proactive strategies to mitigate evolving cyber misuse risks.

Responsibilities

Lead red-teaming exercises across Generative AI models, product surfaces, and autonomous agents to uncover novel cyber misuse capabilities, jailbreaks, and emerging security risks; conduct some red teaming for Frontier Safety risks or content safety as needed.
Design and execute adversarial cyber testing strategies, including evaluations of exploit and malware development uplift, vulnerability discovery, phishing and data-exfiltration enablement, and multi-stage cyber kill chains.
Use technical cyber grading rubrics and safety and security policies to assess attack effectiveness and validate testing strategies; provide technical guidance, baseline grading, and quality oversight for specialized external red-teaming vendors and extended workforce teams.
Analyze, reproduce, and validate testing results, assessing real-world exploitability and capability-uplift severity.
Synthesize technical findings into risk insights and data-driven narratives for cross-functional stakeholders.