Research Scientist, Generative Audio

• Join Spotify's Artist-First AI Music Lab, pioneering state-of-the-art generative technologies for music that create breakthrough experiences for fans and artists. • Conduct groundbreaking research in generative audio using diffusion or flow matching models across areas including vocal synthesis, post-training alignment, and audio editing. • Run large-scale experiments with access to Spotify's extensive infrastructure and an audience of more than 700 million monthly active users. • Work on products that put artists and songwriters first through partnerships with labels, choice in participation, fair compensation, and deepening artist-fan connections. • Hiring across all levels of seniority.

• Hold a PhD in Computer Science, Mathematics, Engineering, or a related field. • Have experience in one or more of generative modelling, machine learning, music information retrieval, speech processing, audio processing, signal processing, probabilistic modelling, computer vision, or related areas. • Have deep expertise in at least one focus area — vocal/speech synthesis, post-training alignment techniques (e.g. PPO, GRPO, DPO), or audio-to-audio generation and text-guided music editing. • Have publications at leading conferences such as ICASSP, ISMIR, INTERSPEECH, ICLR, AAAI, IJCAI, NeurIPS, ICML, CVPR, ECCV, ICCV, or related venues. • Have strong coding skills in Python, PyTorch, and NumPy. • Be a creative problem solver passionate about building outstanding products that add real value to millions of people. • Be enthusiastic about turning research ideas into products operating at scale. • Explain complex topics in simple terms and enjoy building strong relationships with colleagues and stakeholders.

• Have previous industry experience alongside your PhD. • Have experience with preference alignment methods such as DPO, RLHF, or KTO, and reward model design and training. • Have experience with iterative music generation and audio editing capabilities such as stem replacement, instrumentation change, mood changes, tempo changes, and structure changes. • Have experience publishing and presenting at top-tier research conferences. • Have experience running large-scale ML experiments on extensive compute infrastructure.

• Conduct groundbreaking research in generative audio using diffusion or flow matching models, focusing on vocal synthesis, post-training alignment, and/or audio editing. • Run large-scale experiments with access to Spotify's extensive infrastructure. • Create practical applications that harness generative technologies and push the boundaries of what's possible in listening experiences. • Collaborate as part of a cross-functional team working closely with scientists, engineers, product managers, designers, user researchers, and analysts. • Have a direct impact on Spotify's products, tools, and services, working on projects that influence the entire organisation. • Engage with the broader research community by publishing findings, delivering talks, and attending top conferences.

• Work remotely from anywhere in the EMEA region where Spotify has a work location. • Collaborate within Central European and GMT time zones, with core hours of CET 3pm–6pm. • Receive extensive learning opportunities through Spotify's dedicated GreenHouse team. • Receive flexible share incentives letting you choose how you share in Spotify's success. • Receive six months of global parental leave for all new parents. • Access All The Feels, the employee assistance programme and self-care hub. • Swap public holidays flexibly according to your values and beliefs.

Spotify is the world's most popular audio streaming subscription service with more than 700 million monthly active users. The Artist-First AI Music Lab pioneers generative technologies for music through upfront partnerships with labels and publishers, artist choice in participation, fair compensation, and tools that deepen artist-fan connections.