Research Scientist, Gemini Information Tasks

We are seeking a Research Scientist to advance Gemini’s information-task capabilities, focusing on post-training methods such as reinforcement learning and supervised fine-tuning.
You will work on improving the quality, grounding, and factuality of information-seeking responses.
The role involves exploring fundamental modeling and data interventions for information-seeking scenarios and developing novel evaluation metrics.
Key responsibilities include researching post-training approaches, evaluating model quality, and advancing the orchestration of tool calls and retrieval methods.
You will collaborate across research and product surfaces and may contribute to model-external interventions as opportunities arise.
Applicants should have a PhD or equivalent research/publication record and strong software-engineering skills; experience with RL and LLMs for information-seeking is advantageous.