Research Scientist, Gemini Safety

About the job

Responsibilities

• Post-training and instruction tuning state-of-the-art LLMs across text-to-text, image/video/audio-to-text modalities, and agentic capabilities.
• Exploring data, reasoning, and algorithmic solutions to ensure Gemini Models are safe, maximally helpful, and work for everyone.
• Improving Gemini's adversarial robustness, with a focus on high-stakes abuse risks.
• Designing and maintaining high-quality evaluation protocols to assess model behavior gaps and headroom related to safety and fairness.
• Developing and executing experimental plans to address known gaps or construct new capabilities.
• Driving innovation and enhancing understanding of Supervised Fine Tuning and Reinforcement Learning fine-tuning at scale.

Requirements

• PhD in Computer Science or a related field, or equivalent practical experience.
• Significant LLM post-training experience.
• Experience in Reward modeling and Reinforcement Learning for LLMs Instruction tuning.
• Experience with Long-range Reinforcement learning.
• Experience in areas such as Safety, Fairness, and Alignment.
• Track record of publications at NeurIPS, ICLR, ICML.
• Experience taking research from concept to product.
• Experience with collaborating or leading an applied research project.
• Strong experimental taste and good judgment regarding baselines, ablations, and what is worth testing.
• Experience with JAX.