Square Financial Services is looking for a Data Scientist to support the credit policies and machine learning models that power their banking and lending business, aiming to increase credit availability to more sellers sustainably.
Requirements
- Advanced proficiency with SQL and Python for data analysis
- Experience designing and evaluating experiments at scale
- Ability to turn unstructured business problems into concrete analyses that yield actionable insights and recommendations
- Working understanding of core ML concepts, ideally with some experience evaluating or otherwise working with production models
- Experience defining and building product metrics in data visualization tools (e.g. Looker, Mode)
Responsibilities
- Analyze large datasets using SQL and Python to surface actionable insights that directly inform our product and credit strategy
- Approach problems from first principles, using a variety of statistical and mathematical modeling techniques to research and understand customer behavior and loan performance
- Design and analyze A/B experiments and employ pseudo-experimental techniques like causal inference and difference-in-difference
- Use SQL and Python to identify and curate new data sources for modeling, making sense of messy datasets and bringing clarity to business decisions
- Partner closely with ML engineers throughout the modeling lifecycle to develop, deploy, evaluate, and monitor models and credit policies
- Maintain and improve our systems for simulating the impacts of model/policy changes and the decision engine that implements those rules in production
- Build, visualize and report on metrics that drive strategy and facilitate decision making for key business initiatives
Other
- Minimum of 8 years of related experience with a Bachelor's degree; or 6 years and a Master's degree; or a PhD with 3 years experience; or equivalent experience.
- A background in Statistics, Mathematics, Biostatistics, Economics or related quantitative field
- Effectively communicate your work with team leads and cross-functional stakeholders on a regular basis
- Previous exposure to or interest in finance is helpful but not required
