# Security Lead, Agentic Red Team

**Company**: Google DeepMind
**Location**: Mountain View, California, US; New York City, New York, US
**Work arrangement**: onsite
**Experience**: senior
**Job type**: full-time
**Salary**: $248,000 - $349,000 + bonus + equity + benefits
**Category**: Engineering
**Industry**: Technology
**Wikidata**: https://www.wikidata.org/wiki/Q15733006

**Apply**: https://job-boards.greenhouse.io/deepmind/jobs/7560787
**Canonical**: https://yubhub.co/jobs/job_d63f049e-ad7

## Description

Job Title: Security Lead, Agentic Red Team

We're a team of scientists, engineers, and machine learning experts working together to advance the state of the art in artificial intelligence. Our mission is to close the 'Agentic Launch Gap'; the critical window where novel AI capabilities outpace traditional security reviews.

As the Security Lead for the Agentic Red Team, you will direct a specialized unit of AI Researchers and Offensive Security Engineers focused on adversarial AI and agentic exploitation. Operating as a technical player-coach, you will architect complex, multi-turn attack scenarios while managing cross-functional partnerships with Product Area leads and Google security to influence launch criteria.

Key Responsibilities:

* Direct Agile Offensive Security: Lead a specialized red team focused on rapid, high-impact engagements targeting production-level AI models and systems.
* Perform Complex AI Exploitation: Develop and carry out advanced attack sequences that focus on vulnerabilities unique to GenAI, such as escalating privileges through tool usage, poisoning data, and executing multi-turn prompt injections.
* Design Automated Validation Systems: Collaborate with Google teams to engineer 'Auto RedTeaming' solutions that transform manual vulnerability discoveries into robust, automated regression testing frameworks.
* Engineer Technical Countermeasures: Create innovative defense-in-depth frameworks and control systems to mitigate agentic logic errors and non-deterministic model behaviors.
* Manage Threat Intelligence Assets: Develop and oversee an evolving inventory of exploit primitives and agent-specific attack patterns used to establish release criteria and evaluate model security benchmarks.
* Establish Security Scope: Collaborate with Google for conventional infrastructure protection, allowing the team to concentrate solely on agentic logic, model inference, and AI-centric exploits.

About You:

* 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.

In addition, the following would be an advantage:

* Hands-on experience developing exploits for GenAI models (e.g., prompt injection, adversarial examples, training data extraction).
* Familiarity with AI safety benchmarks and evaluation frameworks.
* Experience writing code (Python, Go, or C++) to build automated security tools or fuzzers.
* Ability to communicate complex probabilistic risks to executive stakeholders and engineering teams effectively.

The US base salary range for this full-time position is between $248,000 - $349,000 + bonus + equity + benefits.

## Skills

### Required
- 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
- Proven ability to work in a consulting capacity with product teams
- Experience managing or technically leading small, high-performance engineering teams

### Nice to have
- Hands-on experience developing exploits for GenAI models
- Familiarity with AI safety benchmarks and evaluation frameworks
- Experience writing code (Python, Go, or C++) to build automated security tools or fuzzers
- Ability to communicate complex probabilistic risks to executive stakeholders and engineering teams effectively