Security Lead, Agentic Red Team

Core responsibilities:

• Direct a specialized red team focused on rapid, high-impact engagements targeting production-level AI models and systems
• Develop and carry out advanced attack sequences focusing on vulnerabilities unique to GenAI, such as escalating privileges through tool usage, poisoning data, and executing multi-turn prompt injections
• Design automated validation systems by collaborating with Google teams to engineer "Auto RedTeaming" solutions that transform manual vulnerability discoveries into robust, automated regression testing frameworks
• Engineer technical countermeasures by creating innovative defense-in-depth frameworks and control systems to mitigate agentic logic errors and non-deterministic model behaviors

This role drives the evolution of AI safety by bridging manual exploration with automated regression pipelines, ensuring non-deterministic risks are identified, measured, and mitigated before deployment, ultimately helping to close the "Agentic Launch Gap" where novel AI capabilities outpace traditional security reviews.

Required skills and experience:

• Bachelor's degree in Computer Science, Information Security, or equivalent practical experience
• Experience in Red Teaming, Offensive Security, or Adversarial Machine Learning
• Deep technical understanding of LLM architectures and agentic workflows (e.g., chain-of-thought reasoning, tool usage)
• Proven ability to work in a consulting capacity with product teams, driving security improvements in fast-paced release cycles
• Experience managing or technically leading small, high-performance engineering teams

The US base salary range for this full-time position is between $248,000 - $349,000 + bonus + equity + benefits. At Google DeepMind, we value diversity of experience, knowledge, backgrounds and perspectives and harness these qualities to create extraordinary impact. We are committed to equal employment opportunity regardless of sex, race, religion or belief, ethnic or national origin, disability, age, citizenship, marital, domestic or civil partnership status, sexual orientation, gender identity, pregnancy, or related condition (including breastfeeding) or any other basis as protected by applicable law.