New: upload your resume and get matched to AI jobs. Free to start →

Senior Security Engineer, Agentic Red Team

$174k - $252k • Mountain View, CA, USA; New York, NY, USA; Zürich, Switzerland • Full-time

Posted 26d ago

Job Location

Mountain View, CA, USA; New York, NY, USA; Zürich, Switzerland

Tech Stack

Remote Work Policy

On-site

Employment Type

Full-time

Categories

AI Agent Engineer

About the job

At Google DeepMind, we are building the world's first general-purpose learning agent and are seeking a Senior Security Engineer to join our Agentic Red Team. This specialized unit within DeepMind Security focuses on closing the "Agentic Launch Gap" – the critical window where novel AI capabilities outpace traditional security reviews. You will be the primary technical executor of adversarial engagements, working with product builders to identify architectural flaws early in the design phase. Your core focus will be performing multi-turn attacks on production-level AI models, specifically targeting agentic behaviors like tool usage and reasoning chains. You will not only find vulnerabilities but also contribute to Auto Red teaming frameworks and defensive strategies, codifying your findings into reusable guardrails for all Google agent developers.

Responsibilities

  • Conduct rapid security assessments on agentic services, focusing on vulnerabilities unique to Generative AI such as prompt injection, tool-use escalation, and autonomous lateral movement.
  • Engineer and execute attack sequences that exploit non-deterministic model behaviors, agentic logic errors, and data poisoning vectors.
  • Write code to transform manual vulnerability discoveries into automated regression testing frameworks ("Auto Red Teaming") that prevent regression in future model versions.
  • Partner directly with developers during the design and build phases to provide immediate feedback, shortening the feedback loop between offensive findings and defensive engineering.
  • Maintain and expand a library of agent-specific attack patterns and exploit primitives to establish release criteria for new models.
  • Create systems for agent testing using 2D and 3D games.
  • Develop test problems within physics simulators.
  • Create graphical visualization of results.
  • Build competitive agent leaderboards.
  • Test new algorithms on robots.

Requirements

  • 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 (LLM) architectures, agentic workflows (e.g., chain-of-thought reasoning), and AI vulnerability classes.
  • Experience developing exploits for GenAI models (e.g., prompt injection, adversarial examples, training data extraction).
  • Strong foundation in software engineering.
  • Ability to translate complex probabilistic risks into actionable engineering fixes for developers.
  • Excellent coding skills in Python, Go, or C++ with experience building security tools or automation.

Benefits

  • 15% bonus target
  • equity
  • benefits

About Google DeepMind