Machine Learning Engineer, Personalization

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, podcasts, and audiobooks better than anyone else so that we can make great recommendations to every individual person 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" as well as original playlists such as "Discover Weekly" and "Daily Mix."

Hulk stands for Human Understandable Language Knowledge. The team owns critical assets that power recommendation and distribution across Spotify. We are part of the LLM Foundations Product Area, and we heavily use modern AI techniques and LLMs to derive the best possible understanding of content and set up reliable and scalable systems for distributing that knowledge across partner Spotify teams

What You'll Do

• Be a technical leader within the team you work with and within Spotify in general
• Coordinate technical projects across teams within Spotify
• Facilitate collaboration with other engineers, product owners, and designers to solve interesting and challenging problems for delivering various media worldwide
• Be a valued member of an autonomous, cross-functional agile team
• Architect, design, develop, and deploy ML models that will serve podcast recommendations across the Home, Podcast Subfeed, and NPV surfaces.
• Be a leader in Home's ML community and work collaboratively and efficiently within Home's existing platforms and systems.

Who You Are

• You have experience being a technical leader or mentor
• You have a strong background in machine learning, especially experience with recommender systems.
• You have experience in designing and building ML systems at Spotify (including experience in spotify-kubeflow and salem)
• You are experienced with feature engineering and building scalable data pipelines in Scio.
• You have a deep understanding of ML systems and infrastructure.
• You have experience in Tensorflow or PyTorch. Experience with Kubeflow, Ray is a plus.

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.