Generative Audio Research Scientist — Vocal Synthesis (Equity)

Spotify AB; New York (NY); On-site; USD 133,000 - 190,000; Full time

Benefits offered by this job

Health insurance

Six months parental leave

401(k) retirement plan

Monthly meal allowance

23 paid days off

13 paid holidays

Job summary

Spotify is seeking Research Scientists across all seniorities to advance state-of-the-art generative audio technologies in the Artist-First AI Music Lab. You will conduct groundbreaking research in vocal synthesis, post-training alignment, and audio editing, while collaborating with engineers, product managers, designers, and researchers.

You will publish findings, present at top conferences, and contribute to practical applications at scale for millions of listeners and artists worldwide.

Qualifications

• Ph.D. required or equivalent research experience.
• Experience in generative modeling, ML, MIR, speech/audio processing, or related areas.
• Deep expertise in at least one focus area (vocal/speech synthesis, post-training alignment, or audio-to-audio generation).
• Publications at leading conferences (ICASSP, ISMIR, INTERSPEECH, NeurIPS, ICML, CVPR, etc.).
• Strong coding skills in Python, PyTorch, and NumPy.
• Creative problem solver with passion for impactful products and collaboration.

Responsibilities

• Conduct groundbreaking research in generative audio with diffusion or flow matching methods.
• Run large-scale experiments using Spotify's infrastructure and datasets.
• Publish findings, present talks, and engage with the research community.
• Collaborate with cross-functional teams—engineers, PMs, designers, and researchers.
• Translate research ideas into scalable products and experiments.

Skills

Python

PyTorch

NumPy

Generative modeling

Machine learning

Music information retrieval

Speech processing

Audio processing

Signal processing

Probabilistic modeling

Computer vision

Education

Ph.D. in Computer Science, Mathematics, Engineering, or a related field

Job description

Spotify is seeking Research Scientists across all seniorities to advance state-of-the-art generative audio technologies in the Artist-First AI Music Lab. You will conduct groundbreaking research in vocal synthesis, post-training alignment, and audio editing, while collaborating with engineers, product managers, designers, and researchers.

You will publish findings, present at top conferences, and contribute to practical applications at scale for millions of listeners and artists worldwide.