Backend Engineer II - Native Ads - Music

Native Ads builds promotional tools that artists and their teams use to grow their fanbases on Spotify. We sell products like Marquee and Showcase via Spotify for Artists, helping artists reach listeners across the Spotify consumer app. Behind these formats is a sophisticated ecosystem of forecasting, targeting, supply optimization, and campaign delivery infrastructure that powers millions of promotional campaigns.   We are looking for a Backend Engineer II with strong data engineering skills to join the OptiMyst squad within the Native Ads Performance pillar. OptiMyst's mission is to maximize delivered revenue by understanding, optimizing, and generating predictive insights about our supply of listeners; enabling us to meet customer demand and performance goals.   Our squad sits at the intersection of backend systems and data-intensive ML infrastructure. We build the forecasting models that predict campaign outcomes (reach, clicks, listener conversions), the supply allocation systems that determine how impressions are distributed across campaigns, and the pacing algorithms that optimize delivery in real time. Your work will directly shape how thousands of campaigns perform and how artists invest in growing their audiences.   What You'll Do

Design, build, and operate backend services and large-scale data pipelines that power Native Ads forecasting, supply allocation, and campaign delivery optimization.

Develop and maintain the data infrastructure behind ML forecasting models that predict campaign reach, clicks, conversions, and supply availability across segments, surfaces, and markets.

Build systems that enable forecasting at scale; supporting bulk buying workflows, multi-subcampaign budget allocation, and high-throughput forecast serving for internal and external customers.

Contribute to supply optimization systems including campaign pacing, business-aware supply allocation, and auction infrastructure to maximize delivered revenue and yield.

Collaborate with data scientists and ML engineers to productionize prediction models, build feature pipelines, and ensure model outputs are reliable and observable in production.

Help drive improvements to data quality, pipeline reliability, and system observability across the forecasting and delivery stack.

Work in a cross-functional, agile squad alongside product managers, data scientists, and other engineers to continuously experiment, iterate, and deliver on squad objectives.

Who You Are

You have 3+ years of professional experience in backend engineering, with meaningful exposure to data engineering or ML infrastructure.

You are proficient in at least one backend language such as Java, Scala, or Python, and have experience building services and data pipelines that operate at scale.

You have experience with distributed data processing frameworks (e.g., Scio, Apache Beam, Spark, Flink, or Dataflow) and are comfortable working with large-volume, heterogeneous datasets.

You are familiar with cloud data platforms, ideally GCP, including tools like BigQuery, Cloud Storage, Pub/Sub, and Dataflow.

You understand data modeling, pipeline orchestration, and the tradeoffs between batch and streaming architectures.

You care about data quality, system reliability, and building infrastructure that downstream consumers, whether ML models, product surfaces, or business stakeholders, can trust.

You are excited to work at the boundary of backend systems and data/ML, and are eager to deepen your skills in both areas.

You thrive in collaborative, cross-functional environments and are comfortable navigating ambiguity as requirements evolve.

You have a growth mindset and are energized by the prospect of seeing your work directly impact how artists promote their music to millions of listeners.

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 time zone for collaboration.