Senior Machine Learning Engineer, Personalization

<span>The Personalization team makes deciding what to play next easier and more enjoyable for every listener. From Discover Weekly to AI DJ, we’re behind some of Spotify’s most-loved features. We built them by understanding the world of music and podcasts better than anyone else. Join us and you’ll keep millions of users listening by making great recommendations – and providing valuable context – to each and every one of them.</span><br/><span>Do you want to help Spotify invent new personalized sessions with generative voice AI to delight users? In this role, you’ll work with Spotify’s Text-to-Speech (TTS) team, Speak, to create generated voice audio that enriches users’ experience of music and podcast recommendations.</span> <h3>What You'll Do</h3> <ul> <li>Collaborate with a multidisciplinary team to optimize machine learning models for production use cases, ensuring they are highly efficient and scalable</li><li>Design and build efficient serving infrastructure for machine learning models that supports large-scale deployments across different regions</li><li>Optimize machine learning models in Pytorch or other libraries for real-time serving and production applications</li><li>Lead the effort to transition machine learning models from research and development into production, working closely with researchers and machine learning engineers</li><li>Build and maintain scalable Kubernetes clusters to manage and deploy machine learning models, ensuring reliability and performance</li><li>Implement and monitor logging metrics, diagnose infrastructure issues, and contribute to an on-call schedule to maintain production stability</li><li>Influence the technical design, architecture, and infrastructure decisions to support new and diverse machine learning architectures</li><li>Collaborate with stakeholders to drive forward initiatives related to the serving and optimization of machine learning models at scale.</li></ul> <h3>Who You Are</h3> <ul> <li>You have a passion for speech, audio and/or generative machine learning</li><li>You have world-class expertise in optimizing machine learning models for production use cases, and extensive experience with machine learning frameworks like Pytorch</li><li>You are experienced in building efficient, scalable infrastructure to serve machine learning models, and managing Kubernetes clusters in multi-region setups</li><li>You have a strong understanding of how to bring machine learning models from research to production and are comfortable working with innovative, cutting-edge architectures</li><li>You are familiar with writing logging metrics and diagnosing production issues, and are willing to take part in an on-call schedule to maintain uptime and performance</li><li>You have a collaborative mindset, enjoy working closely with research scientists, machine learning engineers, and backend engineers to innovate and improve model deployment pipelines</li><li>You thrive in environments that require solving complex infrastructure challenges, including scaling and performance optimization</li><li>Experience with low-level machine learning libraries (e.g., Triton, CUDA) and performance optimization for custom components is a bonus</li></ul> <h3>Where You'll Be</h3> <ul> <li>We offer you the flexibility to work where you work best! For this role, you can be within the European region as long as we have <a href="https://lifeatspotify.com/being-here/work-from-anywhere" rel="noopener noreferrer">a work location</a>.</li><li>This team operates within the GMT/CET time zone for collaboration.</li><li>Excluding France due to on-call restrictions.</li></ul>