Senior Data Scientist Recommendations at SoundCloud
Berlin, DE

What's next in music happens on SoundCloud first. As the world’s largest open audio platform, SoundCloud is powered by a connected community of creators, listeners and curators who share, discover and influence what’s new, now and next in music and audio.

We are looking for an impact-driven Data Scientist to solve exciting problems in recommendations and personalization using Machine Learning. Our team builds and maintains systems that empower our users to actively and easily discover SoundCloud's huge and unique catalog of music and audio. You will lead efforts to improve the discover experience with respect to recommendations algorithms, user assistance and user interface in order to enable listeners to discover hidden gems.

Our Data Scientists work on a wide range of products and problems, embedded with engineering teams having direct impact on our millions of daily active users. We want people that come equipped with an open mind, creativity and a get-it-done attitude.


About the role

In this role you will be responsible for leading the efforts to build data products and internal solutions for algorithmic discovery. You will see projects through from start to finish performing research, prototyping solutions, production deployment at scale and A/B testing to validate your solutions. We love specialists with deep experience, and we expect to use that experience alongside a Data Scientist’s ability to be general and tackle a wide range of problem areas.

Some projects you might work on include:

  • Iterate on existing recommendation products to improve quality (e.g. SoundCloud Weekly, More of What You Like, Artists You Should Know)
  • Build recommendation models to empower curation at SoundCloud
  • Advance existing recommendation models by fueling them with curated data
  • Harness the power of the ever increasing data at SoundCloud to build new personalized products
  • Work closely with the Search team on discovery / personalization topics
  • Analyse user journeys and derive success metrics to support product decisions


About You

You are a Data Scientist with a curious analytical mindset, experience with software engineering, and a track record of shipping solutions at large scale. You have a broad toolkit that spans languages and runtimes, and you can get up-to-speed with new tech stacks quickly. You enjoy working cross-functional with Engineers, Product Managers and peer Data Scientists. You have:

  • A Ph.D. or M.Sc. in a quantitative field (Statistics, Machine Learning, AI, Computer Science, Physics, Mathematics, etc.) or demonstrated industry experience productionizing machine learning algorithms
  • A minimum of 5 years of experience in a full-time industry position (not academic) in implementing, evaluating and optimizing recommender systems in different domains. You understand the different objectives a recommender system might have and the best approach for each scenario.
  • A deep understanding of the lifecycle of a Data Science project, with experience in research, solution development, tuning and inspecting models, etc.
  • Experience wrangling very large datasets by writing and maintaining data processing pipelines with Hadoop, Spark, BigQuery, Redshift, or similar
  • Strong engineering background, with experience with Scala, Python or similar languages that are used to ship production models and systems
  • You have solid analytical capabilities; you know not just how to solve problems with machine learning but also where and when
  • Worked in cross-functional teams and are able to work in multiple parts of a tech stack
  • You're able to research and implement the appropriate state of the art algorithms/solutions to the business problems at hand
  • You value the soft-side of applied research (e.g. communication, mentorship, team-work)
  • You are excited by the opportunity to directly impact the daily experience and happiness of millions of people around the world.