The Role

We're seeking a Senior Data Scientist to drive our credit underwriting strategy and risk modeling capabilities. You'll own the development and deployment of machine learning models that power our credit decisions for SMB buyers, working with complex bank transaction data, payment behavior signals, and business financial indicators. This role requires someone who can work end-to-end—from feature engineering and model development to building and maintaining production ML infrastructure.

What You'll Do

Credit Risk Modeling

• Build and optimize predictive models for credit underwriting decisions, default risk assessment, fraud prevention and loss forecasting for SMB businesses
• Develop sophisticated feature engineering pipelines from bank transaction data (ACH, checking/savings patterns, cash flow analysis, etc.)
• Design and implement models to determine optimal credit limits, payment terms (Net 30/60/90), and risk-based pricing
• Analyze cohort performance, loss rates, and develop frameworks for sustainable default rate optimization
• Utilize AI and LLM’s to extract textual bank data and transform it into features.
• Partner with the credit risk team to translate model outputs into actionable underwriting policies

MLOps & Infrastructure

• Own the entire ML lifecycle from development to production deployment and monitoring
• Build scalable, production-grade ML pipelines and infrastructure using modern MLOps best practices
• Implement automated retraining workflows, model versioning, and performance monitoring systems
• Design data pipelines for real-time and batch processing of credit decisions
• Ensure model reliability, latency requirements, and scalability as transaction volumes grow

Cross-Functional Collaboration

• Partner with Product, Engineering, and Credit Risk teams to translate business requirements into technical solutions
• Present findings and recommendations to leadership, external partners and customers.
• Develop data-driven frameworks that balance growth objectives with risk management

Required Experience

• 5+ years of experience in data science, with significant focus on building production ML models
• Strong experience with credit underwriting, credit risk modeling, or lending decisioning—preferably in the SMB/commercial lending space
• Deep expertise in working with bank transaction data, cash flow analysis, and financial statement analysis for creditworthiness assessment
• Proven track record of end-to-end model development: from feature engineering and model training to deployment and monitoring
• Hands-on experience building and maintaining ML infrastructure (MLOps) independently—you can set up training pipelines, deployment systems, and monitoring without needing a dedicated ML engineering team

Technical Skills

• Expert-level proficiency in Python and core data science libraries (pandas, scikit-learn, XGBoost/LightGBM, etc.)
• Strong SQL skills for complex data extraction and feature engineering
• Experience with ML frameworks and model deployment tools (MLflow, Kubeflow, SageMaker, or similar)
• Proficiency with cloud platforms (AWS, GCP, or Azure) and containerization (Docker, Kubernetes)
• Experience with data pipeline orchestration tools (Airflow, Prefect, or similar)
• Comfortable with version control (Git), CI/CD, and software engineering best practices