Minimum qualifications:- PhD degree in Computer Science, Artificial Intelligence, Machine Learning, a related technical field, or equivalent practical experience.
- 1 year experience with Generative AI, Large Language Models, natural language processing, or Agent-based systems.
- 1 year of experience working on modern large language model post-training (e.g., SFT, RLHF, DPO, PPO), model alignment, or core generative model development in an industry AI lab, research institute, or frontier AI organization.
Preferred qualifications:- Experience with reinforcement learning for LLM post-training.
About the jobAs a Research Scientist, you'll setup large-scale tests and deploy promising ideas quickly and broadly, managing deadlines and deliverables while applying the latest theories to develop new and improved products, processes, or technologies. From creating experiments and prototyping implementations to designing new architectures, our research scientists work on real-world problems that span the breadth of computer science, such as machine (and deep) learning, data mining, natural language processing, hardware and software performance analysis, improving compilers for mobile platforms, as well as core search and much more.
As a Research Scientist, you'll also actively contribute to the wider research community by sharing and publishing your findings, with ideas inspired by internal projects as well as from collaborations with research programs at partner universities and technical institutes all over the world.
Individual pay is determined by factors including job-related skills, experience, and relevant education or training.
US: $147000 - $210000 (USD) 15% bonus target equity benefits
Learn more about benefits at Google .
Responsibilities- Improve Gemini with new Reinforcement Learning (RL) environments, evaluations, changes to the RL recipe, or ideas.
- Explore domains where Gemini should be superhuman (e.g., security, hardware, performance engineering, scientific computing, or something we have not thought of) and build the evaluations that show the gap is real.
- Invent new ways of manufacturing hard problems and the graders that make them verifiable.
- Evaluate and train Gemini on your environments, read the trajectories to see what it is actually learning, and land what transfers into production.
- Contribute to identifying and delivering breakthroughs for Gemini.
