Research Scientist, Generative Models - Tokyo

We are seeking a research scientist to join our team dedicated to investigating the development of core technologies for audio generative models. In this role, you will engage in cutting-edge research into core technologies underpinning next-generation generative models, while simultaneously contributing to the rapid integration of these advancements into Google products.

Artificial Intelligence could be one of humanity’s most useful inventions. At Google DeepMind, we’re a team of scientists, engineers, machine learning experts and more, working together to advance the state of the art in artificial intelligence. We use our technologies for widespread public benefit and scientific discovery, and collaborate with others on critical challenges, ensuring safety and ethics are the highest priority.

As a research scientist, you are expected to participate in research initiatives aimed at advancing the core technologies of audio generative models. This undertaking demands close collaboration with research scientists and software engineers, both within the team and across the globe. The objective is to pursue groundbreaking research that balances long-term research aspirations with the immediate needs of users.

Key responsibilities:

• 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, and work with product groups in Google to identify and implement approaches that AI can be used to improve existing and/or create brand-new Google products.
• Report and present research findings and developments clearly and efficiently both internally and externally, verbally and in writing.

In order to set you up for success as a research engineer at Google DeepMind,  we look for 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, including but not limited to audio, images, video, and language.
• Experience coding in one of the following programming languages including but not limited to: Python, C or C++.

In addition, the following would be an advantage:

• Experience in working in the speech and/or acoustic field, e.g. text-to-speech, speech enhancement/separation, automatic speech recognition, and music and environmental sound generation.
• Expertise in relevant research areas, evidenced by publications in high-impact journals and conferences, such as IEEE Transactions, ICASSP, INTERSPEECH, and ML-related conferences.

At Google DeepMind, we value diversity of experience, knowledge, backgrounds and perspectives and harness these qualities to create extraordinary impact. We are committed to equal employment opportunity regardless of sex, race, religion or belief, ethnic or national origin, disability, age, citizenship, marital, domestic or civil partnership status, sexual orientation, gender identity, pregnancy, or related condition (including breastfeeding) or any other basis as protected by applicable law. If you have a disability or additional need that requires accommodation, please do not hesitate to let us know.