Senior Data Scientist, Search and Recommendations at Splice Music
Sr. Data Scientist, Search and Recommendations
- Location: Remote – U.S.
About the role
We are looking for a Sr. Data Scientist to join our Data and Insights team to focus improving our search and recommendation experiences at Splice. In this role, you will define metrics used to track engagement and user-centric outcomes related to search, our content catalog, and recommendation experiences. You will build models that uncover user preferences, with an aim of building more relevant and impactful experiences for our users.
All of this means balancing ad hoc data exploration and longer-running analytical projects; designing and conducting experiments; bridging the gap between Product Managers and Data Engineers to assure that the necessary data is accessible and easy to use; aiding in the design of a roadmap in support of search and recommendations; and building models that support production features.
Skills we’re looking for
In our opinion, things that can be reasonably expressed in SQL, ought to be. We expect our Data Scientists to have strong analytical SQL skills. This means a fluidity constructing statements that rely on a combination of joins, aggregate functions, subqueries, and window functions. This role will work with large-scale data, so this person must have experience writing efficient, performance-optimized queries.
Nearly every problem starts with models that can be interpreted to drive human action. We’re seeking an individual who enjoys experimentation and statistical analysis someone who can translate what they see in the data into useful policy suggestions. A thorough understanding of statistical inference is required.
You should have hands-on experience building machine learning models (supervised and unsupervised) and know how to incorporate your models into production workflows and product experiences. On-the-job experience working regularly with either in-product search data or building recommender platforms is required.
- Regular usage of a programming language typically used for statistical analysis and machine learning (ideally Python). More than a casual familiarity with a statically typed language (ideally Java or Scala) is desirable.
- Strong experience with analytical SQL (ideally BigQuery, Snowflake, or a similar MPP data-warehouse technology).
- Exposure to large-scale model training in a platform like Spark is desired.
- Hands-on experience with self-service product-analytics tools (e.g., Looker, Mixpanel, Amplitude, Heap).
- Training in statistics, econometrics, or machine learning, with plenty of real-world experience applying these methodologies.
- Exposure to a variety of data sets used by Product teams. Chiefly, large-scale event data (e.g., Mixpanel, Segment, Snowplow, server logs) and normalized transactional databases (e.g., e-commerce and subscription datasets).
There are no specific degree requirements for this role: we appreciate and seek out diverse backgrounds. Instead of any particular formal education requirement, we’ll flesh out what you’ve built, what you know, and how you approach problem solving.
As a company that serves musicians and producers, some knowledge of the music-production process is an asset. If this topic is new to you, that’s okay you should be open to learning about it.
Sign up for Daily Remote Job Alerts!