Research Scientist, Audio

About the Team

Members of the team are a group of researchers with core contributions into the Gemini Audio pillar. The team works on audio and audio-visual understanding and generation tasks using large language models.

Key Responsibilities:

• Data: Unlocking new audio to X capabilities within the model
• Models: Improving quality of models for understanding and generation
• Evals: Better evaluation methods to measure quality of open-ended tasks

About You

• PhD in Computer Science, Computer Vision, Speech Processing, or Machine Learning