The Research Scientist role in the Gemini Agent Safety team at DeepMind focuses on developing algorithmic solutions to enhance user-facing architectures. This position requires expertise in Generative AI and aims to ensure that outputs are aligned and production-ready. The team is dedicated to advancing AI safety and model alignment while fostering a culture of collaboration. The role involves both deep research capabilities and practical engineering skills to drive innovations in AI safety.

• PhD in Computer Science, a related field, or equivalent practical experience.
• 1 year experience with Generative AI, Large Language Models, natural language processing, or Agent-based systems.
• Experience in AI safety and model alignment is preferred.
• Expertise in reward modeling, Reinforcement Learning for LLMs, instruction tuning, and long-range RL is preferred.
• A track record of publications at AI/ML venues is preferred.

• Design, implement, and maintain high-quality protocols to identify safety gaps in model behavior across all Gemini and GenAI models.
• Explore, adapt, and apply innovative modeling and alignment techniques to solve real-world safety and alignment challenges.
• Drive innovation in model optimization, advancing the application of Supervised Fine-Tuning and Reinforcement Learning techniques.
• Partner closely with post-training, evaluation, and product teams to align incentives and influence safety decisions.

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