Overview

The centralized Data Science, Engineering, and Analytics team at Recharge delivers critical analytic capabilities and insights that drive the definition and implementation of our and our merchants’ business strategies. The Data Scientist opportunity is ideal for someone who is passionate about data and wants to build end-to-end machine learning models. You will use customer, merchant, and product data, along with external data sources, and billions of dollars of annual processing data to identify patterns that can allow us to accurately predict consumer behavior across our entire merchant base.

As a Data Scientist, you will be responsible for building models from scratch that will then be deployed into production and integrated with our merchant-facing product. You will work closely with our product, engineering, and analytics team to build products that will empower our merchants to make better decisions and grow their businesses.

What you’ll do

• Live by and champion our values: #day-one, #ownership, #empathy, #humility.
• Design, develop, implement, and optimize models that answer key business questions.
• Build, manage and maintain end-to-end models, including data ingestion, data transformation, feature engineering, predictions, model training, hyperparameter tuning, and model deployment.
• Collaborate with product managers to translate business needs into machine learning models and then identify key metrics and baseline performance to evaluate model gains.
• Partner with data engineering and feature teams to gather data from a wide array of disparate sources.
• Manage and maintain our deployed models, including detecting model drift, implementing fixes, and improving performance.

What you’ll bring 

• Typically, 3+ years in a data science related role (Data Scientist, Machine Learning Engineer, Artificial Intelligence Engineer) 
• Track record of building, deploying, and maintaining machine learning models
• Strong proficiency in Python and SQL
• Experience in core mathematical concepts, and core analysis libraries (pandas, seaborn, sklearn, xgboost)
• Basic familiarity with R, or another programming language 
• Experience with Tensorflow is a bonus
• Strong communication skills and stakeholder interaction at engineering, product, and analytic team levels
• M.S./Ph.D in a quantitative field