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!
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.
What is Spotify’s workplace culture like in general?
It doesn’t matter who you are, where you come from or what music you love, at Spotify, you’ll be part of a brand that’s reimagining the entertainment industry. Our open collaborative environment and innovative, audacious brand gives you the opportunity to grow, have fun and do your best work. For an inside look at Spotify’s culture, check out our band manifesto
. What are some of the benefits you offer?
There are benefits to being in our band, and we’re not just talking about free Spotify Premium. Our rewards reflect our inclusive values and are extended to every band member, regardless of location or seniority. ● Extensive learning opportunities, through our dedicated team, GreenHouse. ● Flexible share incentives letting you choose how you share in our success. ● Global parental leave, six months off - fully paid - for all new parents. ● All The Feels, our employee assistance program and self-care hub. ● Flexible public holidays, swap days off according to your values and beliefs. ● Spotify On Tour, join your colleagues on trips to industry festivals and events What is Spotify’s approach to work-life balance?
Some of us work better in the office. Some of us are more productive at home. And many of us find we’re most effective when we have options. Here at Spotify, we don’t just recognize that one-desk-doesn’t-fit-all. We celebrate it with a Work From Anywhere Program that allows you to do just that. We believe we’re happier and more productive when we have the freedom to choose where we work. It helps us find better ways to communicate and collaborate with one another. It means we can work with the very best people for the job, regardless of what city or country they call home. It helps us to become a more diverse place to work, a place that can flex with our people as their lives and ambitions change. And perhaps best of all, it supports a better work-life balance. A life-work balance.