GenAI Red Team Lead & Security Architect

Cyberjobs; Washington (District of Columbia); Presencial; USD 174.000 - 252.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Bonus target

Equity

Benefits

Descripción de la vacante

Google is seeking a Generative AI Senior Security Engineer within the Content Adversarial Red Team (CART) to lead offensive cyber misuse red teaming across Frontier Generative AI products. You will design and execute adversarial evaluations, uncover novel cyber misuse capabilities, and translate results into actionable risk insights for stakeholders.

The role involves cross-team collaboration with Responsible AI Testing and may require extended hours.

Formación

• Bachelor's degree or equivalent practical experience.
• 5 years of experience with security assessments or 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.

Responsabilidades

• Lead red-teaming exercises across Generative AI models, product surfaces, and autonomous agents to uncover cyber misuse capabilities, jailbreaks, and emerging security risks.
• Design and execute adversarial cyber testing strategies, including evaluating exploit and malware development uplift, vulnerability discovery, phishing/data exfiltration enablement, and multi-stage cyber kill chains.
• Apply scoring rubrics and safety policies to determine effectiveness of attacks and provide guidance for external red-teaming vendors and extended workforce teams.
• Analyze, reproduce, and validate testing results, assessing exploitability and uplift severity in real-world contexts.
• Synthesize technical findings into risk insights and data-driven narratives for cross-functional stakeholders.

Conocimientos

Security assessments

Security design reviews

Threat modeling

Security engineering

Network security

Security protocols

Coding in general-purpose languages

Team leadership or risk analysis

Python scripting

Threat intelligence

Educación

Bachelor's degree

Herramientas

Python

Descripción del empleo

Google is seeking a Generative AI Senior Security Engineer within the Content Adversarial Red Team (CART) to lead offensive cyber misuse red teaming across Frontier Generative AI products. You will design and execute adversarial evaluations, uncover novel cyber misuse capabilities, and translate results into actionable risk insights for stakeholders.

The role involves cross-team collaboration with Responsible AI Testing and may require extended hours.