About the role

Staff Data Scientist building production ML models for Mercury’s small-business lending program. Turning financial data into underwriting decisions with Credit, Product, and Engineering.

Responsibilities

Build and own models behind the small business lending program, including transaction classification, recurring inflow/outflow detection, annual revenue estimation, seasonal forecasting, and anomaly detection
Turn bank transactions, storefront sales, and other messy data streams into a defensible view of business health
Deploy models into production with observability, monitoring, and tests
Partner with Credit on underwriting policy, including requested data, follow-up information, and uncertainty quantification
Partner with Product on principal sizes, pricing, and repayment terms
Assess where predictive modeling advances the underwriting program
Set the technical bar for ML in Credit

7+ years building ML models
Implemented models that shaped automated decisions with money on the line
Production-grade Python
Depth beyond classification models, such as time series and forecasting, anomaly detection, and NLP models
Proficiency with deep learning, transformers, and LLMs
Strong SQL skills and comfort working in a data warehouse
Ability to explain a model to a credit officer, model validator, PM, and engineer
Ability to set modeling standards for data-science colleagues
Quantitative degree, or the equivalent built some other way
Direct experience modeling on bank transaction data (nice to have)
Experience in small business lending or business credit cards (nice to have)
Experience with revenue-based financing, merchant cash advances, or similar products (nice to have)

Equity (stock options/RSUs)
Benefits
Equal Employment Opportunity employer
Reasonable accommodations throughout the recruitment process for applicants with disabilities or special needs