Senior Security Engineer, Agentic Red Team, DeepMind - Google Careers

Darum lohnt es sich

ph3Senior Security Engineer, Agentic Red Team, DeepMind /h3 pApply /p pNote: By applying to this position you will have an opportunity to share your preferred working location from the following: bMountain View, CA, USA; New York, NY, USA; Zürich, Switzerland /b. /p h3Requirements /h3 ul liBachelor's degree in Computer Science, Information Security, or equivalent practical experience. /li li5 years of experience in Red Teaming, Offensive Security, or Adversarial Machine Learning. /li liExperience with Large Language Model (LLM) architectures, agentic workflows (e.g., chain-of-thought reasoning), and AI vulnerability classes. /li liExperience developing exploits for GenAI models (e.g., prompt injection, adversarial examples, training data extraction). /li /ul h3Preferred qualifications /h3 ul liExperience working in a consulting capacity with product teams or in a fast‑paced "startup-like" environment. /li liFamiliarity with AI safety benchmarks, evaluation frameworks, and fuzzing techniques. /li liAbility to translate complex probabilistic risks into actionable engineering fixes for developers. /li liExcellent coding skills in Python, Go, or C++ with experience building security tools or automation. /li /ul h3About the role /h3 pAs a part of the Agentic Red Team, you are a specialized, high‑velocity unit within DeepMind Security focused 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. /p pYour core responsibilities include: /p ul liConducting 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. /li liEngineering and executing attack sequences that exploit non‑deterministic model behaviors, agentic logic errors, and data poisoning vectors. /li liWriting code to transform manual vulnerability discoveries into automated regression testing frameworks ("Auto Red Teaming") that prevent regression in future model versions. /li liPartnering directly with developers during the design and build phases to provide immediate feedback, effectively shortening the feedback loop between offensive findings and defensive engineering. /li liMaintaining and expanding a library of agent‑specific attack patterns and exploit primitives to establish release criteria for new models. /li /ul pSalary: US: $174,000–$253,000 (USD) + 15% bonus target + equity + benefits. /p h3EEO Statement /h3 pGoogle is proud to be an equal opportunity and affirmative action employer.

We are committed to building a workforce that is representative of the users we serve, creating a culture of belonging, and providing an equal employment opportunity regardless of race, creed, color, religion, gender, sexual orientation, gender identity/expression, national origin, disability, age, genetic information, veteran status, marital status, pregnancy or related condition (including breastfeeding), expecting or parents-to-be, criminal histories consistent with legal requirements, or any other basis protected by law.

See also Google's EEO Policy, Know your rights: workplace discrimination is illegal, Belonging at Google, and How we hire. /p pGoogle is a global company and, in order to facilitate efficient collaboration and communication globally, English proficiency is a requirement for all roles unless stated otherwise in the job posting. /p /p #J-18808-Ljbffr