Research Engineer, Frontier Safety Mitigations

Sourced from aisafetycareers.com

Google DeepMind is hiring a Research Engineer for Frontier Safety Mitigations in London. The role focuses on building classifiers, monitoring systems, and automated red-teaming to detect and mitigate misuse of frontier AI models. You will work on the research-to-deployment pipeline, securing agentic AI systems and advancing adversarial robustness research.

• Build advanced classifiers and data pipelines to detect misuse, owning the end-to-end process from automated evaluation to rapid model iteration.
• Build cross-context monitoring systems to detect coordinated harms, developing novel signal aggregation methods across disparate user sessions.
• Implement data-driven, semi-automated account-level response systems to detect, track, and apply strikes against persistent malicious actors.
• Evaluate and secure agentic AI systems by developing threat models, creating testing environments, and deploying robust mitigations.
• Advance research in automated red-teaming and adversarial robustness, leveraging multi-turn/agentic attacks to uncover misuse vulnerabilities.

• Bachelor's degree in Computer Science, Machine Learning, or a related technical field, or equivalent practical experience.