Senior Speech AI Scientist — Generative Voice

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

Job summary

Spotify is seeking a senior applied research scientist in New York City to lead developments in state-of-the-art speech models and contribute to end-to-end production pipelines.

You will collaborate with engineering and data teams to advance speech synthesis/recognition, explore new ideas, and push the frontiers of speech technology while working in a hybrid environment with some in-person meetings.

Qualifications

• PhD in ML with professional research experience.
• Experience with transformers, GANs, diffusion models, flow matching, VAEs, or audio codecs.
• Experience developing generative models for speech synthesis/recognition, audio/music, NLP, or computer vision.
• Strong Python and PyTorch skills.

Responsibilities

• Develop and experiment with new methods for speech synthesis and recognition.
• Expand speech use-cases across markets and products.
• Collaborate with engineering/data teams to build scalable pipelines.
• Share research findings with other researchers in Speak.
• Help turn ideas into scalable products.

Skills

ML expertise

Python

PyTorch

Research experience

Communication skills

Education

PhD in ML or related field

Tools

Transformers

GANs

Diffusion models

Flow matching

VAEs

Audio codecs

Job description

Spotify is seeking a senior applied research scientist in New York City to lead developments in state-of-the-art speech models and contribute to end-to-end production pipelines.

You will collaborate with engineering and data teams to advance speech synthesis/recognition, explore new ideas, and push the frontiers of speech technology while working in a hybrid environment with some in-person meetings.