About the Role

Birchbox is seeking an ambitious and experienced Machine Learning Engineer to help evolve our data systems as we continue to grow. In addition to fueling our recommender system and beauty box optimization toolkit, our data services enable and support decision making company wide. This software engineering role will have end-to-end impact on our systems, from data sourcing to algorithm research, from software development to production service deployment.

Primary upcoming initiatives include refreshing our algorithmically-driven subscription box optimization system, iterating on our e-commerce recommender engines, retooling our event data collection systems, and supporting the next generation of our A/B testing machinery.

Responsibilities

• Maintain and iteratively improve the recommender systems that drive our personalized online shop experience (Python, Scala, Spark).
• Develop and deploy improvements to the algorithms underlying Birchbox subscription personalization, and build software tools used by our subscription operations team (Python, Ruby, MILP, CP).
• Help maintain the data processing workflows feeding our personalization and BI systems (SQL, Python, Luigi, Airflow, Pentaho, Redshift, Looker). Build reliable integrations with internal systems and third-party APIs as needed.
• Monitor performance and usability of data systems, ensuring that SLOs are met.
• Keep up with industry trends and best practices, and continually suggest improved strategies and initiatives.
• Support data analysts as needed, advising them on data definitions and helping them derive meaning from complex datasets.

Skills and Qualifications

• 3+ years of professional software experience (or equivalent).
• Expert in Python, and comfortable with at least two of: Scala, R, Ruby, Java.
• Fluency in the statistical underpinnings of machine learning algorithms and linear programming, and experience implementing models as services.
• Strong command line skills for working within virtualized machines (bash, tmux / screen, vim / emacs) and for orchestrating distributed infrastructure (e.g., Pig/Hive, S3, Kafka/Kinesis, Redshift).
• Experience working on teams using distributed version control (e.g., Git, Mercurial).
• Advanced SQL skills (MySQL and/or Postgres), familiarity with data warehousing and dimensional modeling.
• Insatiable curiosity, a commitment to precision and excellence, and a desire to work collaboratively within and between teams.

Good to Have

• MS or PhD in Computer Science, Mathematics, Statistics, or related field.
• Knowledge of principles of Extreme Programming or other paradigms for reliable iterative software development.
• Interest in FOSS, and involvement within the engineering community.
• Opinionated about when and how to leverage different algorithms, data manipulation techniques, and frameworks.