Staff Machine Learning Engineer - Content Intelligence

Have you ever had a debate at a party about who originally wrote a song versus who covered it? Tried to find a sample you loved more than the song you heard it in? Wondered who was actually in the recording booth for your favorite song (on both sides of the glass)? Wonder what Britney Spears, Nsync, Pink, Katy Perry, Taylor Swift, and The Weeknd all have in common? (The same songwriter wrote Billboard number-one singles for all of them). Who gets paid every time we sing “Happy Birthday”?
Music attribution at scale is one of the great unsolved technical problems of the music industry, and we’re building groundbreaking technology to solve it. Our goal is to solve this problem for the more than 60 million music tracks playable on Spotify, building a knowledge graph through machine learning models, deep domain expertise, and close integration with human-in-the-loop processes across Spotify and the industry. Content Platform’s catalog data powers Spotify experiences from Artist pages in the app, search and recommendations, human playlist curation, Spotify for Artists, and our music industry strategy!
We are looking for a Staff Engineer to help us define and build Spotify’s Music Knowledge Graph. The team is composed of product, machine learning, data and backend engineers, and domain experts who average 11 years behind the scenes in the music industry. We expand the state of the art in AI-based machine technology, which enables thoughtful, efficient, and intuitive ways to search, re-use, explore or process metadata. You will use world-class engineering and machine learning techniques on real-world, internal, and external big data to directly impact the evolution of our music catalog! 

What you'll do

• Oversee and guide the design, development, and evolution of our knowledge graph ecosystem.
• Coordinate with Product and Engineering leadership to identify both the long-term and short-term needs of the knowledge graph.
• Build and deploy robust ML/DL models that improve entity extraction, classification, resolution, and disambiguation within the Music Knowledge Graph across multiple languages (e.g. English, Korean, etc.), time dimensions, and territories.
• Collaborate with data engineers, applied ML engineers, software engineering, data/content analysts, research scientists & front-end engineers to support tooling for an increasing number of Music Knowledge Graph use cases within Spotify.
• Collaborate with technical and non-technical business partners to develop analytics and metrics that describe the performance of matching systems and the quality of our data.
• As a multi-functional resource, you will have the opportunity to work on the problems where you are needed most, whether that is with an existing project or cutting a path for something new.
• Take on complex data-related problems involving some of the most diverse datasets available and determine the feasibility of projects through quick prototyping with respect to performance, quality, time, and cost using Agile methodologies.
• Architect best-in-class infrastructure (platforms, tools, and approaches) to accelerate our research to the production phase and to unblock efficient deployment, optimization, and testing of ML models.
• Be a leading voice in an active community of machine learning practitioners across Spotify and use existing state-of-the-art tooling in the Spotify ecosystem. (TensorFlow, Kubeflow, DataFlow, python-beam, Google Cloud Platform).
• Contribute to our team-wide product ideation in collaboration with other engineers, researchers, product managers, and subject-matter experts on the team.
• Your critical projects will involve building enriched canonical versions of the knowledge graph from discrete data sources.

Who you are

• Extensive experience working in a product and data-driven environment (Python, Scala, Java, SQL, or C++, with Python experience required) and cloud platforms (GCP or AWS).
• Understand storage solutions and when to use them (e.g. Graph Database, Cassandra, Relational database).
• Familiarity with Graph ML and graph learning problems & solutions (e.g., graph embedding and graph neural networks).
• Deep expertise in graph building, graph processing, graph querying, and graph analytics.
• You have experience architecting data pipelines and are self-sufficient in getting the data you need to build and evaluate models, using tools like Dataflow, Apache Beam, or Spark.
• Academic and/or proven experience in knowledge graphs, data management, natural language processing.
• Familiar with the industry trends and keep up with the latest product offerings, and can understand trade-offs of existing solutions.
• Have excellent communication skills and the ability to translate business intuition into data-driven hypotheses that result in impactful engineering solutions.
• Love your customers even more than your code.
• Have experience and passion for mentoring and encouraging collaborative teams.
• Have experience in encouraging a strong engineering culture in an agile environment.

Where you'll be

• We are a distributed workforce enabling our band members to find a work mode best for them!
• Where in the world? For this role, it can be within the Americas region in which we have a work location.
• Prefer an office to work from home instead? Not a problem! We have plenty of options for your working preferences. Find more information about our Work From Anywhere options here.
• Working hours? We operate within the Eastern Standard time zone for collaboration.

Spotify is an equal opportunity employer. You are welcome at Spotify for who you are, no matter where you come from, what you look like, or what’s playing in your headphones. Our platform is for everyone, and so is our workplace. The more voices we have represented and amplified in our business, the more we will all thrive, contribute, and be forward-thinking! So bring us your personal experience, your perspectives, and your background. It’s in our differences that we will find the power to keep revolutionizing the way the world listens.
Spotify transformed music listening forever when we launched in 2008. Our mission is to unlock the potential of human creativity by giving a million creative artists the opportunity to live off their art and billions of fans the chance to enjoy and be passionate about these creators. Everything we do is driven by our love for music and podcasting. Today, we are the world’s most popular audio streaming subscription service with a community of more than 381 million users.
This position is not eligible to be performed in Colorado.