Senior Data Scientist

• Build and enhance credit scorecards for underwriting/pricing and risk management, using approaches including logistic regression, and ML methods such as XGBoost.
• Own model monitoring in production, including stability and drift (PSI/CSI), performance (AUC/KS, calibration, segmentation), and outcome tracking across vintages and key cohorts.
• Establish and maintain champion/challenger frameworks, thresholds, and alerting to support proactive risk management.
• Partner with engineering/product to deploy models and supporting pipelines reliably (feature generation, versioning, reproducibility, and release controls).
• Drive model explainability and transparency-produce clear model documentation, rationale, limitations, and operational guidance for internal and external stakeholders.
• Support model governance activities: validation support, performance reviews, change control, and audit-ready artifacts aligned to model risk expectations.
• Integrate fair lending and responsible AI considerations into modeling workflows (disparate impact monitoring, explainability, documentation, and controls aligned with applicable guidance).
• Collaborate with analytics, actuarial, product, and data platform teams to improve data quality, feature availability, and decisioning impact.
• Identify emerging risk trends and deliver actionable insights to leadership (portfolio shifts, macro sensitivity, policy/strategy implications).

We are seeking a technically strong, highly accountable Senior Data Scientist to lead the development and oversight of credit risk scorecards used in production decisioning and pricing. In this role, you will build and maintain traditional scorecard approaches and machine learning models, and you will own the end-to-end lifecycle: data exploration, model development, validation, deployment partnership, and ongoing monitoring.

The ideal candidate has 5-7+ years of hands-on experience building and deploying credit scorecards at a bank, lender, or auto finance environment, and is comfortable operating within model governance expectations (model risk management, documentation, and fair lending considerations). Experience with Databricks is a plus but not required., * 5-7+ years of experience building, validating, and deploying credit risk scorecards (bank, lender, or auto finance strongly preferred).

• Strong proficiency in Python for modeling and production-oriented analytics (pandas/Polars, scikit-learn, XGBoost, etc.).
• Experience with scorecard modeling workflows: binning, WOE/IV, variable selection, regularization, calibration, reject inference familiarity, segmentation, and stability analysis.
• Proven ability to deploy and monitor models end-to-end, including metrics, dashboards, and automated reporting/alerting.
• Working knowledge of fair lending / model governance expectations in credit modeling (documentation, monitoring, change management, and stakeholder communication).
• Comfort working with large datasets and SQL-based environments; ability to collaborate on scalable pipelines with engineering/data teams.
• Strong written and verbal communication skills-able to explain modeling decisions to technical and non-technical audiences.
• Nice to have: Databricks (Spark/PySpark, MLflow), Azure-based data ecosystems, feature store patterns, MLOps experience, Power BI/Tableau.

Open Lending provides automated lending services to financial institutions, leveraging the power of Machine Learning and predictive analytics to deliver risk-based pricing - all backed by the security of our insurance carrier partners.

Before taking the company public in 2020, Open Lending ranked among Austin’s fastest-growing, privately held companies. Starting in 2013, the company placed for seven consecutive years on the Austin Business Journal’s Fast 50 list. Additionally, Open Lending has been named as a top workplace by both the Austin Business Journal and the Austin American Statesman.