Senior Agentic Red Team Security Engineer

Google LLC; Mountain View, New York (CA, NY); On-site; USD 174,000 - 252,000; Full time

Job summary

Google DeepMind is seeking a Senior Security Engineer for the Agentic Red Team. You will be the primary technical executor of adversarial engagements, performing multi-turn attacks on production AI models and helping close the loop with Auto Red Teaming frameworks.

You will collaborate with product teams to identify architectural flaws early in the design phase and craft reusable guardrails for a safer, more secure deployment of agentic AI capabilities.

Qualifications

• Bachelor's degree in Computer Science, Information Security, or equivalent practical experience.
• 5 years of experience in Red Teaming, Offensive Security, or Adversarial Machine Learning.
• Experience with Large Language Model architectures, agentic workflows, and AI vulnerability classes.

Responsibilities

• Conduct rapid security assessments on agentic services focusing on Generative AI vulnerabilities.
• Engineer and execute attack sequences against production-level AI models.
• Develop automated regression testing frameworks to prevent regression in future model versions.
• Collaborate with developers during design/build phases to provide immediate feedback.
• Maintain a library of agent-specific attack patterns and guardrails.

Skills

Red Teaming

Adversarial ML

LLM security

Python/Go/C++

Education

Bachelor's degree in CS/Info Sec

Tools

Auto Red Teaming frameworks

Job description

Google DeepMind is seeking a Senior Security Engineer for the Agentic Red Team. You will be the primary technical executor of adversarial engagements, performing multi-turn attacks on production AI models and helping close the loop with Auto Red Teaming frameworks.

You will collaborate with product teams to identify architectural flaws early in the design phase and craft reusable guardrails for a safer, more secure deployment of agentic AI capabilities.