Summary

Senior applied research scientist role focused on speech synthesis, speech recognition, and generative models for Spotify's platform. The role uses Python and PyTorch alongside transformers, diffusion models, GANs, VAEs, and audio codecs, with a hybrid arrangement in London or Stockholm.

Responsibilities

• Develop speech synthesis methods
• Experiment with speech recognition models
• Build generative models for audio
• Collaborate on data and infrastructure
• Improve speech processing pipelines
• Scale proven research into products