The Research Engineer for Frontier Safety Mitigations at DeepMind focuses on developing safety measures for AI models to prevent misuse in critical areas such as cybersecurity and harmful manipulation. This role is part of a collaborative team dedicated to building robust defenses against severe risks associated with AI technology. The engineer will work on creating advanced evaluations and deploying mitigations while ensuring the beneficial use of AI. The position emphasizes a proactive approach to researching and implementing safety strategies.

• 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.
• Master's degree or PhD in Computer Science or a related technical field is preferred.

• Build advanced classifiers and data pipelines to detect misuse.
• Develop cross-context monitoring systems to identify large-scale attack vectors.
• Implement data-driven, semi-automated account-level response systems against malicious actors.
• Evaluate and secure agentic AI systems by developing threat models and testing environments.
• 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.