About the job
As a Scorecard Developer at Tyme, you will be instrumental in the development and maintenance of credit scoring components and their calibrations that underpin our approval and risk strategies across various products and markets. Your primary objective will be to create high-quality features, ensuring that scores are both stable and explainable, while delivering robust Probability of Default (PD) to bad-rate calibrations that convert model outputs into actionable risk measures.
Key Responsibilities
· Develop and maintain scoring solutions and supporting artifacts utilized in credit decision-making, including application and behavioral scoring, segmentation, and risk signals.
· Take ownership of feature engineering for scoring by creating, testing, and documenting variables derived from bureau, application, transactional, and repayment data, ensuring stability, interpretability, and data quality.
· Contribute to model development and tuning using advanced machine learning techniques, ensuring that outputs are robust, stable, and suitable for decision-making.
· Implement best-in-class machine learning practices for credit scoring, including disciplined hyperparameter optimization, robust validation processes, and repeatable model selection workflows suitable for production decisioning.
· Define and maintain feature specifications for production, addressing definitions, transformations, edge-case handling, missing value logic, and consistency checks.
· Generate PD/score calibrations to match observed bad rates, including calibration curves, stability monitoring, and recalibration recommendations.
· Assist in cutoff/limit strategy analysis utilizing calibrated risk outputs (approval rate vs. bad rate vs. loss trade-offs).
· Conduct ongoing monitoring of input/feature drift and stability, score distribution changes, performance by segment and cohort/vintage, and data pipeline health.
· Collaborate with Engineering and Decisioning teams to operationalize scoring outputs and ensure reproducibility through versioning, back-testing, and change control.
· Maintain thorough documentation appropriate for internal review and audit, including feature catalogs, calibration approaches, monitoring reports, and change logs.

