Scorecard Developer (Machine Learning Specialist) - Bengaluru

Overview

Develop and maintain credit scoring components and calibrations that support approval and risk strategies across products and markets, focusing on stable, explainable scores and robust PD-to-bad-rate calibrations.

What you'll do

• Develop and maintain scoring solutions and supporting artefacts used in credit decisioning (application and/or behavioural scoring, segmentation, risk signals).
• Own feature engineering for scoring: create, test and document variables from bureau, application, transactional and repayment data; ensure stability, interpretability and data quality.
• Contribute to model development and tuning using modern machine learning approaches where appropriate, ensuring outputs are robust, stable and suitable for decisioning.
• Apply best-in-class machine learning practices for credit scoring, including disciplined hyperparameter optimisation, robust validation, and repeatable model selection workflows appropriate for production decisioning.
• Define and maintain feature specifications for production (definitions, transformations, edge-case handling, missing value logic, consistency checks).
• Produce PD / score calibrations to observed bad rates (overall and by segment), including calibration curves, stability tracking, and recalibration recommendations.
• Support cut-off / limit strategy analysis using calibrated risk outputs (approval rate vs bad rate vs loss trade-offs).
• Run ongoing monitoring: drift and stability of inputs/features, score distribution shifts, performance by segment and cohort/vintage, data pipeline health.
• Partner with Engineering / Decisioning teams to operationalise scoring outputs and ensure reproducibility (versioning, back-testing, change control).
• Maintain clear documentation suitable for internal review/audit (feature catalogue, calibration approach, monitoring packs, change logs).

What you'll need

• 2–4 years' experience in credit scoring / risk modelling / decisioning analytics in a lender, bank, bureau, or fintech setting.
• Strong SQL plus Python/R for feature engineering, analysis, monitoring and calibration work.
• Practical experience with advanced machine learning concepts (e.g., ensemble methods, feature selection, hyperparameter tuning, cross-validation) and the discipline to balance predictive power with stability and governance needs.
• Experience translating model outputs into business-ready risk measures via calibration and performance tracking.
• Ability to produce implementation-ready specifications and work closely with engineering/decisioning stakeholders.

Nice to have

• Exposure to multi-country portfolios and different bureau ecosystems.
• Familiarity with model risk governance, validation support, and evidence pack preparation.
• Experience with real-time/batch scoring pipelines and feature stores.

Details

• Reports to: Credit Risk Modelling Lead / Scorecards Lead.
• Location: Mumbai, India; collaboration with product and in-country credit risk teams.