The Research Engineer for the Frontier Safety Mitigation team at DeepMind will focus on developing advanced safety mitigations for frontier AI models. This role involves working in a collaborative environment to build robust defenses against critical misuse domains such as cybersecurity and harmful manipulation. The team is dedicated to ensuring the safe deployment of AI technologies while addressing emerging risks. The position requires a strong background in software development and experience in AI safety research.

• Bachelor's degree or equivalent practical experience.
• 5 years of experience with software development in one or more programming languages.
• 3 years of experience testing, maintaining, or launching software products.
• 1 year of experience with software design and architecture.
• Experience working across the research-to-deployment pipeline in a frontier AI environment.

• Build advanced classifiers and data pipelines to detect misuse.
• Develop cross-context monitoring systems to detect coordinated harms.
• Implement data-driven, semi-automated account-level response systems.
• Evaluate and secure agentic AI systems by developing threat models.
• Advance research in automated red-teaming and adversarial robustness.

• Employees at Google are often offered benefits like comprehensive health insurance, 401(k) matching, and flexible work arrangements, among other benefits.