Senior Speech AI Research Scientist – Generative Voice

Spotify; Greater London; Ibrido; GBP 100.000 - 140.000; Tempo pieno

Descrizione del lavoro

Spotify is seeking a senior applied research scientist to advance state-of-the-art generative speech-to-speech models within the Speak team in London or Stockholm. You will work across the production pipeline, combining research ideas with engineering to scale high-fidelity voice synthesis and recognition.

You have a PhD in ML and extensive experience with transformers, diffusion models, VAEs, and audio codecs, plus Python and PyTorch, and you can communicate complex concepts to technical and

Competenze

• PhD in ML or related field; strong track record in research.
• Experience with speech, audio or ML model development is advantageous.
• Excellent communication and ability to explain complex ideas.
• Experience collaborating across research and engineering teams.

Mansioni

• Develop and experiment with new methods for speech synthesis and recognition.
• Work on end-to-end approaches and production-ready pipelines.
• Expand speech use-cases across markets and products.
• Collaborate with engineering and data teams to scale models.
• Share research findings and best practices with the Speak team.

Conoscenze

PhD in ML/AI

Transformers

Diffusion models

GANs

VAEs

Audio codecs

Python

PyTorch

Formazione

PhD in ML/AI or related field

Strumenti

PyTorch

Python

Descrizione del lavoro

Spotify is seeking a senior applied research scientist to advance state-of-the-art generative speech-to-speech models within the Speak team in London or Stockholm. You will work across the production pipeline, combining research ideas with engineering to scale high-fidelity voice synthesis and recognition.

You have a PhD in ML and extensive experience with transformers, diffusion models, VAEs, and audio codecs, plus Python and PyTorch, and you can communicate complex concepts to technical and