Note: By applying to this position you will have an opportunity to share your preferred working location from the following:
Mountain View, CA, USA; New York, NY, USA; Zürich, Switzerland.
- 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).
- Experience working in a consulting capacity with product teams or in a fast-paced "startup-like" environment.
- Familiarity with AI safety benchmarks, evaluation frameworks, and fuzzing techniques.
- 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.
At Google DeepMind our mission is to build the world's first general-purpose learning agent. Central to this mission is the complex task of measuring the intelligence of our prototypes. As a Software Engineer, you will be working with the cutting edge AI agents developed by our exceptional team of Machine Learning and Neuroscience research scientists. Your responsibilities will include everything from creating systems for agent testing using 2D and 3D games to developing test problems within physics simulators. You will create graphical visualization of results, build competitive agent leaderboards and test new algorithms on robots. To succeed in this role you will need to have a strong foundation in software engineering and enjoy working on a wide range of challenging problems within a mission-driven team.
As a part of the Agentic Red Team, you will be a specialized, high-velocity unit within DeepMind Security. Your mission is to close the Agentic Launch Gap—the critical window where novel AI capabilities outpace traditional security reviews.
As a Senior Security Engineer on the Agentic Red Team, you will be the primary technical executor of adversarial engagements. You will work with product builders, identifying architectural flaws during the design phase long before formal reviews begin.
Your core focus will be to perform 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 help close the loop by contributing to Auto Red teaming frameworks and defensive strategies, ensuring that your findings are codified into reusable guardrails for all Google agent developers.
Artificial intelligence will be one of humanity’s most transformative inventions. At Google DeepMind, we are a pioneering AI lab with exceptional interdisciplinary teams focused on advancing AI development to solve complex global challenges and accelerate high-quality product innovation for billions of users. We use our technologies for widespread public benefit and scientific discovery, ensuring safety and ethics are always our highest priority.
We are pushing the boundaries across multiple domains. Our global teams offer diverse learning opportunities and varied career pathways for those driven to achieve exceptional results through collective effort.
Individual pay is determined by factors including job-related skills, experience, and relevant education or training.
US: $174000 - $253000 (USD) + 15% bonus target + equity + benefits
Learn more about benefits at Google.
- Conduct rapid, high-impact 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, effectively 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.
Google is proud to be an equal opportunity workplace and is an affirmative action employer. We are committed to equal employment opportunity regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity or Veteran status. We also consider qualified applicants regardless of criminal histories, consistent with legal requirements. See also Google's EEO Policy and EEO is the Law. If you have a disability or special need that requires accommodation, please let us know by completing our Accommodations for Applicants form.
