c6c0a57f-a27 Research Scientist, Gemini Information Tasks We are seeking a research scientist to precisely improve Gemini's information-seeking capabilities. The successful candidate will work on post-training research in Gemini, focusing on quality of information-seeking responses. This role offers an opportunity to explore fundamental issues in modelling and data interventions for information-seeking scenarios, with significant opportunities in shaping Google's products in this space.

Responsibilities:

  • Conduct research on post-training methods for information-seeking scenarios in Gemini, including reinforcement learning and self-supervised training.
  • Develop novel evaluation methods for improving model quality, grounding, and factuality.
  • Investigate orchestration of tool calls and improved retrieval methods for information-seeking scenarios.

Requirements:

  • PhD in a relevant area, or an equivalent research/publication record.
  • Strong software-engineering skills in addition to a research background.

Preferred Qualifications:

  • Experience in reinforcement learning.
  • Experience in post-training methods.
  • Experience in Large Language Models for information-seeking scenarios.

The US base salary range for this full-time position is between $147,000 USD - 211,000 + bonus + equity + benefits.

XML job scraping automation by YubHub

]]> full-time senior onsite $147,000 USD - 211,000 + bonus + equity + benefits PhD in a relevant area, Strong software-engineering skills, Reinforcement learning, Post-training methods, Large Language Models, Experience in reinforcement learning, Experience in post-training methods, Experience in LLMs for information-seeking scenarios Engineering Technology Google DeepMind https://logos.yubhub.co/deepmind.com.png Google DeepMind is a subsidiary of Alphabet Inc. focused on artificial intelligence research. https://deepmind.com/ https://job-boards.greenhouse.io/deepmind/jobs/7669124 Mountain View, California, US 2026-04-18 ac8db56d-335 Research Scientist, Gemini Information Tasks We are seeking a Research Scientist to drive research in Gemini for information tasks. This role involves working on post-training innovations to improve the quality, groundedness, and factuality of Gemini models in search mode. The successful candidate will contribute to improving helpfulness and factuality of Gemini models, impacting product surfaces including AI Mode, Gemini App, AI Studio, and Vertex AI.

Key responsibilities include researching post-training methods such as reinforcement learning and self-supervised training for information-seeking scenarios in Gemini, developing novel evaluation methods for improving model quality, grounding, and factuality, and researching orchestration of tool calls and improved retrieval methods for information-seeking scenarios.

To succeed in this role, you should have a PhD in a relevant area or an equivalent research/publication record, strong software-engineering skills, and experience in reinforcement learning, post-training methods, and LLMs for information-seeking scenarios.

XML job scraping automation by YubHub

]]> full-time senior onsite PhD in a relevant area, Reinforcement learning, Post-training methods, LLMs for information-seeking scenarios, Software-engineering skills Engineering Technology Google DeepMind https://logos.yubhub.co/deepmind.com.png Google DeepMind is a subsidiary of Alphabet Inc. focused on artificial intelligence. https://deepmind.com/ https://job-boards.greenhouse.io/deepmind/jobs/7450900 New York City, New York, US 2026-03-16