The Research Scientist in Safety Oversight at DeepMind focuses on ensuring the safety and alignment of deployed AI models. This new team utilizes large-scale production data and automated evaluation methods to monitor AI model safety. The role involves collaboration with various teams to address model safety issues and enhance the efficacy of safety measures. The position is critical in advancing AI development while prioritizing safety and ethics.

• PhD in Computer Science, a related field, or equivalent practical experience.
• 3 years of experience building and shipping technical products.
• Experience in the domain area of generative AI and Large Language Models (LLM).
• Master’s degree or PhD in Engineering, Computer Science, or a related technical field is preferred.
• 3 years of experience developing code, running experiments and analyses collaboratively with coding agents.

• Build classifiers and large-scale data pipelines to detect model misbehavior and misuse end-to-end.
• Research and develop cross-context monitoring systems to detect coordinated harms.
• Develop novel signal aggregation methods across disparate user sessions to identify large-scale attack vectors.
• Think critically about novel methods for monitoring using model activations and actions.
• Collaborate closely with infrastructure teams and data scientists to scale your work.

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