Data Scientist

About Birchbox:

Founded in 2010, Birchbox is a leading beauty and grooming retailer, offering an efficient, personalized way to discover and shop for new products. We redefined the e-commerce experience by pairing a monthly subscription of samples with a curated online shop featuring more than 800 best-in-class brands. Every month, subscribers receive five prestige samples tailored to their unique profile along with inspiring editorial content that creates a seamless path to purchase full-size versions of their favorites on Birchbox.com. In 2012, we launched Birchbox Man and expanded internationally, and in 2014, we opened our first brick-and-mortar store in Soho. Today we have more than one million subscribers and operate in six countries, including France, Spain, UK, and Belgium. Birchbox is headquartered in New York City.

The Data Science, Analytics and Insights team is comprised of data scientists, data engineers and statistical analysts aiming to help Birchbox change the way people discover products via deep personalization, smart recommendation, and great data-driven decisions overall. As a data scientist in the team, your projects range across the full spectrum of Machine Learning and Applied Statistics.

The Data Scientist at Birchbox will be responsible for:

  • Monthly box personalization: tailoring the selection of samples sent to each Birchbox subscriber
  • Full-size product recommendation: based on purchasing and browsing history, samples received, reviews, profile etc.
  • Improvements to product and content search and sorting
  • Prediction of subscriber churn, sample conversion, shop activation, etc.
  • Working with analysts and other teams to deliver insights to inform major product and business decisions

A successful Data Scientist candidate at Birchbox will have:

  • 1-3 years of experience as a data scientist
  • Fluency in a scripting language such as Python for fast prototyping
  • Strong understanding of classification, clustering and recommendation algorithms
  • Ability to write complex SQL queries in short order
  • Experience with Map/Reduce tools (e.g. Hadoop, Pig, Hive)
  • Solid understanding of a wide range of open source data mining / machine learning / data visualization software packages (e.g. pandas, scikit-learn, matplotlib, Spark
  • Deep working experience applying statistics and machine learning research and techniques to real-world data


  • Proficiency in R, Matlab, or another mathematical language
  • Familiarity with various factorization models (e.g. matrix factorization, factorization machines)
  • Experience with integer programming, search technologies, natural language processing
  • Experience with designing and deploying ETL to ingest data into data warehouse
  • Knowledge of distributed algorithms and how to analyze them
  • Java, Scala know-how

Back to top