Staff Data Scientist - Credit and Lending ML

About this role

Build and own machine-learning models that support Mercury’s small-business lending decisions, using data such as bank transactions, sales, and financial reporting. Deploy models with appropriate testing and monitoring, and partner with Credit and Product on underwriting policy and lending-product design.

About the company

Mercury provides banking and financial software for startups, combining business accounts, cards, and money-management tools designed for venture-backed companies.

What you'll do

• Build models for transaction classification, cash-flow detection, revenue estimation, forecasting, and anomaly detection
• Turn messy business data into a defensible assessment of borrower health
• Deploy production models with observability, monitoring, and tests
• Partner with Credit on underwriting policy, data collection, and uncertainty assessment
• Partner with Product on loan sizes, pricing, and repayment terms
• Assess where predictive modeling can improve underwriting
• Set technical standards for machine learning in Credit

What we're looking for

• 7+ years of experience building machine-learning models
• Experience implementing models that influence automated decisions with financial consequences
• Production-grade Python and strong SQL skills
• Expertise beyond classification, such as time-series forecasting, anomaly detection, or NLP
• Proficiency with deep learning, transformers, and LLMs
• Ability to explain models to credit, validation, product, and engineering stakeholders
• Ability to set modeling standards for data-science colleagues
• Quantitative degree or equivalent experience

Nice to have

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