GenAI Senior Security Engineer, Red Team
Seattle, WA, USA +2 · Senior · Full-time · Posted Oct 28, 2026
- Location
- Seattle, WA, USA
Austin, TX, USA
Washington D.C., DC, USA - Experience
- 5 years in security assessments/design reviews/threat modeling; 5 years in security engineering/computer and network security/security protocols; 5 years coding; 1 year in technical leadership or enterprise technical risk analysis.
- Education
- Bachelor's degree or equivalent practical experience.
About the job
Leads offensive cyber red teaming of Google’s frontier generative AI products, evaluates cyber misuse risks, and communicates findings to stakeholders.
What you'll do
- Lead adversarial evaluations of generative AI models, products, and agents to identify cyber misuse capabilities and security risks.
- Design and conduct tests involving exploit and malware development, vulnerability discovery, phishing, data exfiltration, and multi-stage cyber kill chains.
- Validate results, oversee testing quality, and turn technical findings into risk insights for cross-functional stakeholders.
What they ask for
- 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 leading technical teams or technical risk analysis in an enterprise environment.
Nice to have
- Experience in offensive security and red-team operations, and evaluating or stress-testing generative AI, LLM agents, or AI/ML systems.
- Python production or testing experience, or a background in threat intelligence, anti-abuse engineering, or cyber kill-chain analysis.
Pay
$174000 - $252000 (USD) base salary; 15% bonus target (USD)
Tools
Python, Generative AI, LLM agents, AI/ML
AI focus
Red-team testing of generative AI products and agents for cyber misuse, jailbreaks, prompt injection, and emerging security risks.
Model-written summary · the original posting is authoritative