The Senior Staff Research Scientist role at DeepMind focuses on rethinking safety post-training for advanced AI models. The position requires expertise in machine learning and safety methodologies, particularly in agentic settings. The scientist will collaborate closely with the AGI Safety team to ensure that Gemini models are safe and aligned. This role is critical as AI systems evolve to perform complex, long-horizon tasks.

• PhD in Computer Science, a related field, or equivalent practical experience.
• 6 years of experience in Machine Learning Algorithms and Language Modeling.
• One or more scientific publications in ML/AI conferences or journals.

• Rethink how safety is trained into models, especially for agentic, long-horizon behavior.
• Design and ship post-training recipes that install safety and alignment properties into Gemini models.
• Build the metrics and evaluations that assess the safety of models in deployment.
• Work directly with the post-training pipeline and infrastructure.
• Shape the road map for future safety post-training initiatives.

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