Machine Learning Engineer - Content Platform (Remote Eligible)

Spotify is looking for a Machine Learning Engineer to join the Content Platform team! Content Platform is a central enabler for Spotify. Together, our teams ensure that Spotify has a complete, available, and enriched catalog of music, podcasts, videos, and more. Sitting at the intersection of our consumer and creator offerings, we use a combination of cutting-edge machine learning, crowd-sourced wisdom, and deep industry expertise to discover and organize structured information about the world of audio. In doing so, we help Spotify make well-informed decisions and build impactful products.

We are looking for an ML Engineer to join our team that is working on applying and experimenting with state-of-the-art machine learning techniques to improve the quality of Spotify’s catalog content. As an engineer on the team, you will not only coordinate and influence the direction within the team but also work with multiple stakeholders to drive and deliver ML-centric products.

What you’ll do

• Contribute to designing, building, evaluating, shipping, and improving Spotify’s products through hands-on ML development in Python, SQL, Scala, and Java (but mostly Python + SQL).
• Collaborate with a cross-functional agile team spanning data science, product management, music industry experts, and engineering to build new product features that improve the quality of our catalog.
• Work with a senior MLE on the team to prototype new ML approaches and production-ize solutions at scale using the Google Cloud Platform, including Kubeflow.
• Perform data analysis to establish baselines and inform product decisions.
• A desire to communicate and explain the role of your machine learning work to the larger team as well as stakeholders.
• Be part of a growing group of machine learning practitioners across Spotify and within Content Platform.

Who you are

• You have a strong background in machine learning and software engineering, with experience and expertise in designing, building, and testing models.
• Experience with machine learning solutions in a production environment and has demonstrated the ability to deliver results making tradeoffs between idealistic approaches and product impact.
• Experience with disparate data sources, both structured and unstructured. An understanding of how to manipulate and join these datasets in creative ways.
• You have hands-on experience implementing production machine learning systems at scale in Java, Scala, Python, or similar languages.
• Experience with Java microservices that will contribute to backend development and help guide the team towards best practices with our machine learning solutions.
• Lead the model design and keep the team aligned with ML infrastructure while maintaining a focus on impact and delivery.
• Familiarity with reinforcement learning approaches is a big plus.
• Previous industry experience with frameworks such as Tensorflow and the Tensorflow ecosystem (TFX) is also a plus. Kubeflow experience also a plus.
• Experience with data pipeline tools like Apache Beam, Scio, etc., and cloud platforms like GCP or AWS.
• Experience with building data pipelines and getting the data you need to build and evaluate your models, using tools like Apache Beam is a plus.
• You care about agile software processes, data-driven development, reliability, and responsible experimentation.