Machine Learning Engineer II - P2P - Personalization
Description
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 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 to each and every one of them.
Prompted Playlists (P2P) let listeners describe exactly what they want to hear and set the rules for their personalized playlist experience. This feature taps into a listener’s entire Spotify history—stretching back to day one—to reflect not just what they love now, but the full arc of their taste. The team blends personalization, world knowledge, and adaptive curation to deliver playlists that stay fresh, relevant, and delightful. P2P is looking for an experienced ML engineer to join the team!
What You'll Do
Design, build, evaluate, and ship LLM based solutions that will enable our users to have more adaptive control of their content Collaborate with cross functional teams spanning user research, design, data science, product management, and engineering to build new product features that advance our mission to connect artists and fans in personalized and useful ways Prototype new approaches and productionize solutions at scale for our hundreds of millions of active users Promote and role-model best practices of ML systems development, testing, evaluation, etc., both inside the team as well as throughout the organization Be part of an active group of machine learning practitioners
Who You Are
An experienced ML practitioner motivated to work on complex real-world problems in a fast-paced and collaborative environment - Strong background in machine learning, natural language processing, and generative AI, with experience in applying theory to develop real-world applications Hands-on expertise with implementing end-to-end production ML systems at scale. Experience with production LLM scale based systems is a plus Experience with incorporating human feedback to improve LLM based systems using technicals like DPO, KTO, and reinforcement fine-tuning Experience with deg end-to-end tech specs and modular architectures for ML frameworks in complex problem spaces in collaboration with product teams Experience with large scale, distributed data processing frameworks/tools like Apache Beam, Apache Spark, and cloud platforms like GCP or AWS
Where You'll Be
We offer you the flexibility to work where you work best! For this role, you can be within the North Americas region as long as we have a work location. This team operates within the Eastern Standard time zone for collaboration.