Senior Applied Research Scientist - Generative Speech AI

Spotify; New York (NY); Hybrid; USD 169,000 - 242,000; Full time

Benefits offered by this job

Health insurance

Six month paid parental leave

401(k) retirement plan

Monthly meal allowance

23 paid days off

13 paid flexible holidays

Job summary

Spotify’s Personalization Speak Team seeks a senior applied research scientist to advance novel ML approaches for speech-to-speech models and scalable production pipelines. You will collaborate with engineering and data teams to explore new ideas, push quality and realism of voice models, and expand speech use-cases across markets and products.

Strong research background and Python/PyTorch expertise are essential.

Qualifications

• PhD in ML or related field with strong research background.
• Experience with speech synthesis/recognition or generative models.
• Proven ability to publish and communicate complex ideas clearly.

Responsibilities

• Develop and experiment with new methods for speech synthesis and speech recognition, along with end-to-end approaches, building on the latest research and ideas.
• Work towards the expansion of our speech use-cases targeting different markets and products.
• Be part of a highly motivated research team dedicated to building and creating models at scale to power the Spotify platform.
• Champion best practices for research and development, sharing your knowledge and experience with other researchers within Speak.
• Collaborate with our engineering and data teams on ideas requiring new infrastructure or new high-quality data, as well as to help improve our speech recognition and speech synthesis pipelines, and help turn proven ideas into scalable products.

Skills

PhD in ML

Transformers

GANs

Diffusion models

Flow matching

VAEs

Audio codecs

Python

PyTorch

Education

PhD in ML or related field

Tools

PyTorch

Python

Job description

Spotify’s Personalization Speak Team seeks a senior applied research scientist to advance novel ML approaches for speech-to-speech models and scalable production pipelines. You will collaborate with engineering and data teams to explore new ideas, push quality and realism of voice models, and expand speech use-cases across markets and products.

Strong research background and Python/PyTorch expertise are essential.