Research Scientist, Gemini Safety

Responsibilities

• Post-training and instruction tuning of state-of-the-art LLMs across text, image, video, and audio modalities
• Exploring data, reasoning, and algorithmic solutions to ensure model safety and helpfulness
• Improving adversarial robustness against high-stakes abuse risks
• Designing and maintaining high-quality evaluation protocols for safety and fairness
• Developing and executing experimental plans to address model gaps or build new capabilities
• Driving innovation in Supervised Fine Tuning and Reinforcement Learning at scale

Requirements

• PhD in Computer Science, a related field, or equivalent practical experience
• Significant LLM post-training experience

Preferred Qualifications

• Experience in Reward modeling and Reinforcement Learning for LLM instruction tuning
• Experience with Long-range Reinforcement learning
• Expertise in Safety, Fairness, and Alignment
• Track record of publications at NeurIPS, ICLR, ICML, RL/DL, EMNLP, AAAI, or UAI
• Experience taking research from concept to product
• Experience leading or collaborating on applied research projects
• Proficiency with JAX

About the Company

At Google DeepMind, we’re a team of scientists, engineers, and machine learning experts working together to advance the state of the art in artificial intelligence for widespread public benefit and scientific discovery.