Senior and Staff Data Scientist - Credit and Lending ML

The role

You will build and own the inference layer for a small business lending program. You will develop models using bank transactions and financial data to inform lending decisions and product shape.

What you will do

• Build and own models for transaction classification, recurring inflow/outflow detection, annual revenue estimation, forecasting, and anomaly detection
• Turn messy data streams into a view of business health
• Deploy models into production with observability, monitoring, and tests
• Partner with Credit on underwriting policy
• Partner with Product on product shape including principal sizes, pricing, and repayment terms
• Assess where predictive modeling moves the underwriting program
• Set the technical bar for ML in Credit

Required qualifications

• Staff: 7+ years building ML models
• Staff: Implemented models that shaped automated decisions with money on the line
• Staff: Write production-grade Python
• Staff: Depth in time series, forecasting, anomaly detection, and NLP models
• Staff: Proficient with deep learning, transformers, and LLMs
• Staff: Strong in SQL and at home in a data warehouse
• Staff: Be able to explain a model to a credit officer, a model validator, a PM, and an engineer
• Staff: Be able to set modeling standards for data-science colleagues
• Staff: Have a quantitative degree, or the equivalent built some other way
• Senior: 3+ years building ML models
• Senior: At least 1 year in lending or credit algorithms
• Senior: Be opinionated and thoughtful on where ML can best lift an underwriting program

Nice to have

• Direct experience modeling on bank transaction data
• Experience in small business lending or business credit cards
• Experience with revenue-based financing, merchant cash advances, or similar products

Benefits

• Base salary
• Equity (stock options/RSUs)
• Benefits

About the company

Mercury is building financial infrastructure for startups and growing businesses. They extend credit to businesses using proprietary access to data like bank transactions, financial reporting, and payroll.