Research Scientist, Generative Models - Tokyo

Google DeepMind is seeking a Research Scientist to join their team in Tokyo, Japan, focusing on the development of core technologies for audio generative models. The Research Scientist will engage in cutting-edge research, contributing to next-generation generative models, and integrating these advancements into Google products.

The role involves close collaboration with research scientists and software engineers globally, balancing long-term research aspirations with immediate user needs. The responsibilities include:

• Research and development of new technologies for audio generative models, including text-to-speech, audio restoration and separation, and music and environmental sound generation.
• Collaborate with other research scientists and engineers to implement prototypes for new products with product groups.
• Report and present research findings and developments clearly and efficiently both internally and externally, verbally and in writing.

Google DeepMind looks for candidates with the following skills and experience:

• PhD in a relevant technical field or equivalent practical experience.
• Research and development experience in media generative and/or restoration models (audio, images, video, language).
• Experience coding in Python, C or C++.

The role offers:

• Opportunity to work at Google DeepMind.
• Engage in cutting-edge research into core technologies underpinning next-generation generative models.
• Collaborate with other research scientists and engineers to implement prototypes for new products.