Credit Risk Modelling Specialist

About the Role

We are looking for a highly skilled Risk Modeling Specialist / Data Scientist to lead the development of sophisticated predictive frameworks. In this role, you will build and deploy the models that power our lending decisions, from fraud detection to credit risk assessment. You will work at the forefront of financial technology, utilizing advanced statistical and machine-learning techniques to optimize our risk-reward balance throughout the customer lifecycle.

Responsibilities

• Strategic/Credit Model Design: Conduct deep-dive business/credit analysis to define model objectives and target variables that align with risk appetite and growth goals.
• Feature Engineering & Data Innovation: Lead data cleaning and the design of complex risk indicators; actively explore alternative data dimensions and emerging business scenarios to improve model precision and predictive power.
• End-to-End Model Development: Develop and calibrate a comprehensive suite of risk scoring models across the credit lifecycle, including anti-fraud models (identity and transaction fraud), application/behavior/collection scoring, and credit limit & pricing models to optimize portfolio performance.
• Monitoring & Decision Support: Implement robust model stability monitoring (PSI, CSI, KS) and translate model outputs into actionable approval strategies and policy recommendations.

Qualifications

• Education: Bachelor’s degree or higher in a quantitative discipline (Statistics, Mathematics, Computer Science, Financial Engineering, or Economics).
• Experience: 5+ years of hands-on modeling experience within Fintech, Payments, Banking, or Consumer/Digital Finance preferred.
• Domain Expertise: Comprehensive understanding of credit risk dynamics across the pre-loan, in-loan, and post-loan stages (Application/Behavior/Collection).
• Strategic Mindset: Proven ability to link model performance to business outcomes and communicate complex technical findings to stakeholders.

Skills

• Expertise in Python (preferred) or SAS/SPSS, and advanced SQL for data manipulation.
• Experience with machine learning frameworks (e.g., XGBoost, LightGBM) and traditional logistic regression.
• Model monitoring and validation practices (PSI, CSI, KS).