Senior Staff Machine Learning Engineer - Agentic Systems

The Personalization team makes deciding what to play next on Spotify easier and more enjoyable for every listener. We seek to understand the world of music and podcasts better than anyone else so that we can make great recommendations to every individual and keep the world listening. Every day, hundreds of millions of people all over the world use the products we build which include destinations like Home and Search, original playlists like Discover Weekly and Daylist, and are at the forefront of new innovations like AI DJ and AI Playlists.

Generative AI is transforming Spotify’s product capabilities and technical architecture. Generative recommender systems, agent frameworks, and LLMs present huge opportunities for our products to serve more user needs and use cases and unlock richer understanding of our content and users. This Senior Staff Machine Learning Engineer will focus on recommender systems modeling at the intersection of generative recommenders and foundational understanding of personalization across music and talk content formats.

You will work closely with a cross-functional team to define and execute the machine learning technical strategy for the product area, building the next generation of Spotify content and user representations and the technical architecture to support it. You will work as an individual contributor, offering the opportunity to shape the direction of Home loading paradigms, page serving, content filtering and content storage. Join us and you’ll keep millions of users listening to great recommendations every day!

What You'll Do Lead the technical architecture of Spotify’s Agent Engine, the shared runtime that powers agent-based experiences across the platform Guide the transition of existing agent-powered features into a unified system, balancing speed, reliability, and real-world product constraints Design how internal systems can be exposed as agent capabilities, enabling seamless integration across recommendations, search, catalog, and more Build and improve evaluation systems that help teams measure quality, reliability, and user impact with confidence Partner with research and machine learning teams to define what belongs in system design versus model capabilities Explore and prototype new approaches to agent-based systems, and bring successful ideas into production at scale Support best practices in building production-ready AI systems, including experimentation, observability, and performance optimization Contribute to technical standards that help teams move faster while maintaining security and reliability Stay connected to advances in the AI and machine learning community, and apply relevant ideas to Spotify’s products Who You Are You have experience building and scaling production AI systems, including systems powered by large language models You are comfortable working across system design, infrastructure, and machine learning concepts, and enjoy connecting these areas You have experience with areas such as agent orchestration, LLM infrastructure, evaluation systems, or data pipelines for machine learning You have worked on platform or consolidation efforts that bring multiple systems or teams together You are able to make progress in ambiguous problem spaces and bring structure to open-ended challenges You communicate clearly and work well with engineering, product, and research partners across different levels of the organization You stay informed on developments in AI and are motivated to apply new ideas in practical ways You take a pragmatic approach to building, using prototypes and iteration to move ideas forward You take ownership of outcomes and proactively manage risks, trade-offs, and expectations Where You'll Be We offer you the flexibility to work where you work best! For this role, you can be within the North America region as long as we have a work location This team operates within the Eastern Standard time zone for collaboration