Research Scientist - Generative Audio

Spotify is a Swedish audio streaming and media service provider founded in 2006. With over 751 million monthly active users and 290 million paying subscribers, it is one of the largest music streaming services globally. Spotify is listed on the New York Stock Exchange.

Introduction

Spotify is seeking Research Scientists at all levels of seniority to join their Artist-First AI Music Lab. This team is at the forefront of generative audio technologies, aiming to create innovative music experiences for fans and artists centered around four key principles: partnerships, user choice in participation, fair compensation, and deepening artist-fan connections. The role involves groundbreaking research in generative audio using diffusion or flow matching models.

Responsibilities

• Conduct groundbreaking research in generative audio using diffusion or flow matching models, focusing on one or more areas:
  • Vocal Synthesis: Research in vocal and speech synthesis, ML-based audio processing, and signal processing.
  • Post-Training: Research in post-training techniques for music generation, including preference alignment methods (such as DPO, RLHF, or KTO), reward model design and training, and reinforcement learning to improve output quality, controllability, and human preference adherence.
  • Editing: Research in iterative music generation and audio editing, including capabilities such as stem replacement, instrumentation change, mood changes (while preserving content), tempo changes, and structure changes.
• Run large-scale experiments utilizing Spotify's extensive infrastructure and its audience of over 700 million monthly active users.
• Create practical applications that leverage generative technologies to push the boundaries of listening experiences.
• Collaborate with a cross-functional team including scientists, engineers, product managers, designers, user researchers, and analysts to develop innovative solutions to complex challenges.
• Directly impact Spotify's products, tools, and services, contributing to projects that influence the entire organization.
• Engage with the broader research community through publications, talks, and conference attendance.

Requirements

• Ph.D. in Computer Science, Mathematics, Engineering, or a related field. Previous industry experience is beneficial.
• Experience in one or more of the following fields: generative modeling, machine learning, music information retrieval, speech processing, audio processing, signal processing, probabilistic modeling, computer vision, or related areas.
• Deep expertise in at least one of the focus areas: vocal/speech synthesis, post-training alignment techniques (e.g., PPO, GRPO, DPO), or audio-to-audio generation and text-guided music editing.
• Publications at leading conferences such as ICASSP, ISMIR, INTERSPEECH, ICLR, AAAI, IJCAI, NeurIPS, ICML, CVPR, ECCV, ICCV, or related venues.
• Strong coding skills in Python, PyTorch, and NumPy.
• Creative problem solver passionate about building impactful products for millions of people.
• Enthusiastic about translating research ideas into scalable products.
• Ability to explain complex topics clearly and build strong relationships with colleagues and stakeholders.

Nice to Have

• Previous industry experience.

Benefits

• Health insurance.
• Six months paid parental leave.
• 401(k) retirement plan.
• Monthly meal allowance.
• 23 paid days off.
• 13 paid flexible holidays.
• Flexibility to work from anywhere within the North Americas region where Spotify has a work location.

About Company

Spotify is a Swedish audio streaming and media service provider founded in 2006. With over 751 million monthly active users and 290 million paying subscribers, it is one of the largest music streaming services globally. Spotify is listed on the New York Stock Exchange.

How to Apply

Click the "Apply for this position" button on the job board. You may also use the Smart Apply option with a profile page.