Backend Engineer - Personalization - Tunesday

Spotify•Boston, MA

26d•Remote

About The Position

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. On the Tunesday squad, our mission is simple! When a user is looking for new music, we help them find the right content at the right time. Every week, hundreds of millions of people discover new artists and tracks through the experiences we build - Discover Weekly, Smart Shuffle, Playlist Extender, and This Is Artist. We are a team of backend & data engineers, data scientists & product experts but most of all, we are passionate about music! As a Backend Engineer on Tunesday, you will own and evolve the systems behind some of Spotify's most-loved playlist experiences. Your work will range from low-latency gRPC services handling real-time recommendation requests, to large-scale daily batch pipelines that process hundreds of millions of user signals to surface the right tracks. You will work closely with data scientists and product managers to bring new recommendation ideas to production and you will help define the engineering bar for how we build and evaluate those experiences.

Requirements

Several years of experience as a Backend Engineer building and operating services at scale
Strong Java skills
Comfort with gRPC and Protocol Buffers
Hands-on experience with large-scale data pipelines, ideally Apache Beam/Scio or a similar batch processing framework (Spark, Flink)
Experience with pipeline orchestration tools like Flyte or similar
Comfortable working across the full backend stack: from online serving (Bigtable, Memcached, low-latency APIs) to offline data (BigQuery, Dataflow, dbt)
Curiosity about recommendation systems, search, or personalization
Care about quality and know what it means to ship reliable, observable, production-grade systems
Think about SLOs, on-call burden, and correctness as part of your design
Thrive in an environment of experimentation and fast iteration
Use data to make decisions and are comfortable working with data scientists to evaluate the impact of changes

Nice To Haves

Experience with GCP (Kubernetes/GKE, Gantry, Dataflow, BigQuery, Bigtable)
Experience with Elasticsearch

Responsibilities

Design and operate services that serve personalized recommendations to users in real time, including Smart Shuffle and Discover Weekly
Build and maintain large-scale batch pipelines in Scala/Scio and Flyte that generate candidate pools, bloom filters, and personalization signals for hundreds of millions of users daily
Develop and maintain components within Spotify's Sessions Platform (SSP) that power playlist experiences end to end, from candidate retrieval to final serving
Collaborate with data scientists to operationalize research ideas, for example, expanding our definition of music discovery beyond simple listening recency, or integrating audio attributes like BPM and musical key into recommendation ranking
Be a technical leader in an autonomous, multi-functional team: drive architecture decisions, set engineering standards, and help the team ship faster with higher confidence