[All remote jobs](https://jobicy.com/jobs.md)[![Spotify logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2021/03/Jobicy-210328105941-289246.jpg)](https://jobicy.com/company/spotify.md)[Spotify](https://jobicy.com/company/spotify.md) # Research Scientist – Generative Audio Review the role, location requirements, compensation details, and application process before deciding whether this opportunity fits your next career move. [Apply for this job](#job-application)[View company](https://jobicy.com/company/spotify.md)ShareRemote from[EMEA](https://jobicy.com/job-region/emea.md)SalaryUndisclosedDepartment[Data Science & Analytics](https://jobicy.com/categories/data-science.md)EmploymentFull TimeExperienceOpen levelPublished13 Oct 2026Apply before12 Nov 2026Listing views37Application actions2Application toolkit ## Make your next move. Prepare your resume, explore your fit, and draft a cover letter for this opportunity. AI Summary ## The role, at a glance. Spotify is hiring a Research Scientist for its Artist-First AI Music Lab to develop generative-audio technologies that improve music creation and listening experiences. The role focuses on vocal and speech synthesis, post-training and preference alignment for music generation, or iterative audio editing. The scientist will run large-scale experiments, translate research into scalable product applications, and collaborate with engineering, product, design, research, and analytics partners. Candidates need a relevant Ph.D., a strong publication record, deep machine-learning or audio-research expertise, and practical Python, PyTorch, and NumPy skills. The role is eligible for people located within EMEA where Spotify has a work location and requires regular Central European/GMT collaboration. ## Role DNA A quick view of the complexity, pace, ownership and collaboration implied by the job description. ### Job Complexity 5/5EasyHard ### Pace & Pressure 4/5RelaxedFast-paced ### Autonomy Level 5/5GuidedFull ownership ### Communication Load 4/5IndependentCollaborative AI insightThis is an advanced research role requiring doctoral-level technical depth, publications at leading ML or audio conferences, and expertise in rapidly evolving generative-audio methods. Success also depends on converting novel research into reliable, high-scale product capabilities. ## Salary analysis Estimated compensation compared with the broader US market for similar roles. Estimated job medianMarket rate$190,000US market range$150k–$250k0$275k AI insightNo salary is disclosed in the posting. These are estimated US annual base-salary benchmarks in USD for a Research Scientist specializing in generative AI/audio; actual compensation may vary substantially by seniority, location, and equity or bonus structure. ## Core skills Skills and capabilities most closely associated with this opportunity. [Generative AI](https://jobicy.com/jobs?search_keywords=Generative%20AI.md)[Generative Audio](https://jobicy.com/jobs?search_keywords=Generative%20Audio.md)[Machine Learning](https://jobicy.com/jobs?search_keywords=Machine%20Learning.md)[Music Generation](https://jobicy.com/jobs?search_keywords=Music%20Generation.md)[Vocal Synthesis](https://jobicy.com/jobs?search_keywords=Vocal%20Synthesis.md)[Speech Processing](https://jobicy.com/jobs?search_keywords=Speech%20Processing.md)[PyTorch](https://jobicy.com/jobs?search_keywords=PyTorch.md)[Python](https://jobicy.com/jobs?search_keywords=Python.md)[Reinforcement Learning](https://jobicy.com/jobs?search_keywords=Reinforcement%20Learning.md)[Signal Processing](https://jobicy.com/jobs?search_keywords=Signal%20Processing.md) Sample interview questionsHow would you evaluate a generative music model beyond standard likelihood or reconstruction metrics?I would combine automated metrics with structured human evaluation. Automated measures could assess audio fidelity, diversity, musical consistency, and adherence to conditioning, while listening studies would measure perceived quality, controllability, artist usefulness, and preference. I would define success criteria by use case and analyze results across genres, prompts, and demographic cohorts. Describe how you would use preference optimization to improve a music-generation model. I would first establish a high-quality preference dataset using expert, artist, or carefully designed listener comparisons. I would train a reward or preference model, validate it for bias and robustness, and then apply methods such as DPO or RL-based optimization with safeguards against reward hacking and diversity collapse. Offline evaluations and controlled online experiments would determine whether the changes improve real user and artist outcomes. What technical challenges arise when building text-guided music editing, such as changing instrumentation while preserving melody? The central challenge is disentangling editable attributes from content that must remain invariant. I would investigate representations that preserve timing, melody, harmony, and structure while allowing localized control over timbre or instrumentation, then train with paired or synthetically generated edits. Evaluation should explicitly test preservation, edit accuracy, audio quality, and failure cases across diverse source material. How would you scale experiments for diffusion or flow-matching audio models? I would begin with reproducible small-scale experiments and clear ablations before expanding to distributed training. Efficient data pipelines, mixed precision, checkpointing, experiment tracking, and standardized evaluation suites are essential. I would also prioritize profiling model bottlenecks and use staged model or sequence-length scaling to manage compute effectively. How do you communicate a complex research result to product and nontechnical stakeholders? I start with the user problem, the decision the team needs to make, and the practical impact of the result. I use simple visual examples or audio demonstrations, explain uncertainty and limitations plainly, and connect technical metrics to user-facing outcomes. I then recommend a concrete next experiment, product direction, or risk mitigation plan. Opportunity details ## About this role. We are seeking Research Scientists (across all levels of seniority) to join our Artist-First AI Music Lab. Our team pioneers and advances state-of-the-art generative technologies for music that create breakthrough experiences for fans and artists. We invent entirely new listening experiences that center and celebrate artists and creatives. All of our products will put artists and songwriters first, through these four principles: * Partnerships with record labels, distributors, and music publishers: We’ll develop new products for artists and fans through upfront agreements, not by asking for forgiveness later. * Choice in participation: We recognize there’s a wide range of views on the use of generative music tools within the artistic community. Therefore, artists and rightsholders will choose if and how to participate to ensure the use of AI tools aligns with the values of the people behind the music. * Fair compensation and new revenue: We will build products that create wholly new revenue streams for rightsholders, artists, and songwriters, ensuring they are properly compensated for the use of their work and transparently credited for their contributions. * Artist-fan connection: AI tools we develop will not replace human artistry. They will give artists new ways to be creative and connect with fans. We will leverage our role as the place where more than 700 million people already come to listen to music every month to ensure that generative AI deepens artist-fan connections. Learn more in our press release: [https://newsroom.spotify.com/2025-10-16/artist-first-ai-music-spotify-collaboration/](https://newsroom.spotify.com/2025-10-16/artist-first-ai-music-spotify-collaboration/) ### What You’ll Do Conduct groundbreaking research in generative audio using diffusion or flow matching models, with a focus on one or more of the following areas: Vocal Synthesis — Research in vocal and speech synthesis, along with related areas such as 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. You will also: * Run large-scale experiments with access to Spotify’s extensive infrastructure and an audience of more than 700 million monthly active users. * 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—to craft innovative solutions to complex challenges. * Have a direct impact on Spotify’s products, tools, and services, working on projects that influence the entire organization. * Engage with the broader research community by publishing your findings, delivering talks, and attending top conferences. ### Who You Are * You have a Ph.D. in Computer Science, Mathematics, Engineering, or a related field. Previous industry experience is helpful. * You have 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. * You have deep expertise in at least one of the focus areas above—whether that’s vocal/speech synthesis, post-training alignment techniques (e.g., PPO, GRPO, DPO), or audio-to-audio generation and text-guided music editing. * You have publications at leading conferences such as ICASSP, ISMIR, INTERSPEECH, ICLR, AAAI, IJCAI, NeurIPS, ICML, CVPR, ECCV, ICCV, or related venues. * You have strong coding skills in Python, PyTorch, and NumPy. * You are a creative problem solver who is passionate about building outstanding products that add real value to millions of people. * You are enthusiastic about turning research ideas into products operating at scale. * You can explain complex topics in simple terms, and you enjoy building strong relationships with colleagues and stakeholders. ### Where You’ll Be * We offer you the flexibility to work where you work best! For this role, you can be within the EMEA region as long as we have[a work location](https://lifeatspotify.com/being-here/work-from-anywhere) * This team operates within the Central European and GMT time zone for collaboration. * Core working hours are CET 3pm-6pm / EST 9am-12pm. ### Compensation ### Additional Information Spotify is an equal opportunity employer. You are welcome at Spotify for who you are, no matter where you come from, what you look like, or what’s playing in your headphones. Our platform is for everyone, and so is our workplace. The more voices we have represented and amplified in our business, the more we will all thrive, contribute, and be forward-thinking! So bring us your personal experience, your perspectives, and your background. It’s in our differences that we will find the power to keep revolutionizing the way the world listens. At Spotify, we are passionate about inclusivity and making sure our entire recruitment process is accessible to everyone. We have ways to request reasonable accommodations during the interview process and help assist in what you need. If you need accommodations at any stage of the application or interview process, please let us know – we’re here to support you in any way we can. Show more [Apply now >](https://jobicy.com/jobs/155214-research-scientist-generative-audio.md) > Annual salary information is not provided for this position. Explore salary ranges for similar roles in our [Salary Directory ›](https://jobicy.com/salaries.md) * ![Upload CV](data:image/svg+xml;base64,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) ### Upload your resume now To unlock remote work opportunities and be discovered by global employers. This job listing has been manually reviewed by the Jobicy Trust & Safety Team for compliance with our posting guidelines, including verification of the company's legitimacy, accuracy of job details, clarity of remote work policy, and absence of misleading or fraudulent content. Next step ## Apply now. Follow the employer’s application method and review Jobicy’s safety guidance before sharing personal information. Keep exploring ## Related remote jobs. * ![Spotify logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2021/03/Jobicy-210328105941-289246.jpg) Spotify Oct 13 New ### [Research Scientist – Personalization](https://jobicy.com/jobs/155216-research-scientist-personalization.md) The Personalization team makes deciding what to play next easier and more enjoyable for every listener. From Blend to Discover Weekly, we’re behind some of Spotify’s most-loved features. We built… * ![Instructure logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2022/04/430057884baf037dd2aa1e1e017e72b6.jpg) Instructure Oct 13 New ### [Senior Decision Scientist](https://jobicy.com/jobs/155187-senior-decision-scientist-2.md) At Instructure, we believe in the power of people to grow and succeed throughout their lives. Our goal is to amplify that power by creating intuitive products that simplify learning… * ![M3 USA logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/e75eef15-221-1.jpg) M3 USA Oct 13 New ### [Project Director, Qualitative Research](https://jobicy.com/jobs/145885-project-director-qualitative-research.md) Company DescriptionAbout M3: A Japanese global leader in the provision of ground-breaking and innovative technological and research solutions to the healthcare industry. The M3 Group operates in the US, Asia, and… * ![1Password logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2020/09/WRILS-200909195848-296323.png) 1Password Oct 13 New ### [Senior GTM Engineering Analyst](https://jobicy.com/jobs/153118-senior-gtm-engineering-analyst.md) 1Password is growing. We’ve surpassed $400M in ARR and we’re continuing to accelerate, earning a spot on the Forbes Cloud 100 for four years in a row and teaming up… * ![Zapier logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2021/03/Jobicy-210317121153-967239.png) Zapier Oct 13 New ### [Manager, GTM Analytics](https://jobicy.com/jobs/153099-manager-gtm-analytics.md) AI at Zapier At Zapier, we build and use automation every day to make work more efficient, creative, and human. So if you’re using AI tools while applying here –… * ![Liftoff logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/c47aea9f-221.png) Liftoff Oct 13 New ### [Product Analyst](https://jobicy.com/jobs/153096-product-analyst.md) Liftoff is a leading AI-powered performance marketing platform for the mobile app economy. Our end-to-end technology stack helps app marketers acquire and retain high-value users, while enabling publishers to maximize… * ![Launch Potato logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/30f8890f-221-1.png) Launch Potato Oct 12 New ### [Lead BI Developer](https://jobicy.com/jobs/155159-lead-bi-developer-2.md) WHO ARE WE? Launch Potato is the discovery and conversion company. We reach tens of millions of people every month through our brands, including FinanceBuzz, All About Cookies, and OnlyInYourState…. * ![Launch Potato logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/30f8890f-221-1.png) Launch Potato Oct 12 New ### [Lead Analytics Manager](https://jobicy.com/jobs/155158-lead-analytics-manager-2.md) WHO ARE WE? Launch Potato is the discovery and conversion company. We reach tens of millions of people every month through our brands, including FinanceBuzz, All About Cookies, and OnlyInYourState…. * ![Launch Potato logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/30f8890f-221-1.png) Launch Potato Oct 12 New ### [Lead BI Manager](https://jobicy.com/jobs/155160-lead-bi-manager-2.md) WHO ARE WE? Launch Potato is the discovery and conversion company. We reach tens of millions of people every month through our brands, including FinanceBuzz, All About Cookies, and OnlyInYourState…. * ![Launch Potato logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/30f8890f-221-1.png) Launch Potato Oct 12 New ### [Business Intelligence Lead, Performance Marketing](https://jobicy.com/jobs/155153-business-intelligence-lead-performance-marketing-4.md) WHO ARE WE? Launch Potato is the discovery and conversion company. We reach tens of millions of people every month through our brands, including FinanceBuzz, All About Cookies, and OnlyInYourState…. [Browse all jobs](https://jobicy.com/jobs.md)