Research Scientist, AudioPaLM, Zurich

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.

Snapshot

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.

About Us

Our team focuses on improving Google's audio and speech generation capabilities. In particular, we work on

• 
  

  Improving Gemini / AudioPaLM to perform better with realtime audio dialog and translation

  
  


• 
  

  Improving audio-based capabilities of Google's large language models in general

  
  


• 
  

  Combining speech generation models and music generation / understanding models into one large conversational language model

  
  


• 
  

  The next generation of our AudioLM and Lyria models

  
  

You can hear some of us talk in the video posted a while back on the AudioPaLM website.

The Role

State-of-the-art audio synthesis relies on powerful generative models like AudioLM, which combine compact discrete representations with language models to synthesize high-quality audio. The responsibilities of someone hired in this role are to:

• 
  

  Explore how to extend Gemini Audio, AudioPaLM, and related models

  
  


• 
  

  Create a universal model that can generate audio and music in any language based on natural instructions

  
  


• 
  

  Design ways to integrate audio generation capabilities with existing large language models such as Gemini

  
  


• 
  

  Design experiments and deploy proof-of-concept demos in the areas described above

  
  


• 
  

  Work with product teams to deploy our research results in Google's products

  
  

About You

In order to set you up for success as a Research Scientist at Google DeepMind, we look for the following skills and experience:

• 
  

  PhD in Computer Science, Machine Learning, a related technical field or equivalent practical experience.

  
  


• 
  

  Experience in Machine Learning, speech and general audio processing.

  
  


• 
  

  Experience in Large Language Models

  
  


• 
  

  Programming experience in Python/C++

  
  


• 
  

  Research Publications at leading conferences/journals. 

  
  

Closing date for applications will be end of Friday 25th April