Senior Applied Research Scientist - Personalization
Core
Developing state-of-the-art generative conversational speech-to-speech models to enhance Spotify's speech recognition, synthesis, and engagement features.
Role type
Senior Applied Research Scientist (Generative Speech)
Builds
Production speech models (recognition, synthesis, speech-to-speech) for Spotify's personalization and creator tools.
Domain
Audio/ML, Generative AI, Speech Technology
Deliverable
production ML models
Required skills
Generative models (transformers, GANs, diffusion models, flow matching, VAEs), Speech synthesis, Speech recognition, PyTorch, Python, End-to-end model development
Preferred skills
Audio codecs, NLP, Computer vision, High-quality research experience
Technologies
PyTorch, Transformers, GANs, Diffusion models, Flow matching, VAEs
Responsibilities
Develop and experiment with new methods for speech synthesis and recognition; Expand speech use-cases across markets; Collaborate with engineering to build scalable production pipelines; Champion research best practices and share knowledge.
Seniority
Senior, hands-on IC with PhD