Postdoctoral Researcher

Company: Meta

City: London

Country: United Kingdom

In this role, you will conduct research on real-time audio-visual speech enhancement and speech-driven animation. You will also publish the research in high impact conferences and deploy the developed models to real world products.

Postdoctoral Researcher Responsibilities:

• Help build the next generation of audio-visual speech enhancement and generative AI models.
• Harness passion for technology and propose new research roadmaps which can lead to the creation of new models that can be applied to multiple applications.
• Make use of advanced knowledge in designing novel deep networks which process audio-visual data.
• Without direct assistance, design real-time audio-visual speech enhancement models that can be used on-device.
• Employ deep knowledge in the following areas: data processing, audio-visual speech enhancement, audio-visual self-supervised learning, speech-driven animation.
• Disseminate findings of research by publishing papers in high impact conferences.

Minimum Qualifications:

• PhD degree in Computer Science, Computer Engineering, Applied Sciences, Mathematics, Physics, or related field.
• Experience in each of the following:
• Python, PyTorch
• Track record of publishing papers in high quality journal and conferences.
• Designing and training large deep networks.
• Data processing of large audio-visual datasets.
• Audio-visual speech enhancement
• Audio-visual self-supervised learning
• Speech-driven facial animation