Credit Risk Model Validation Analyst / Senior Analyst

Role Summary

We are looking for a Credit Risk Model Validation professional with 2–5 years of experience in credit cards, consumer lending, retail finance, banking or fintech. The person will independently review credit-risk models, test their performance, challenge key assumptions and clearly communicate any risks or limitations to business and governance teams.

Key Responsibilities

• Validate underwriting, acquisition, behaviour, collections, fraud and portfolio-risk models.
• Review the full model lifecycle, including:
• Business purpose and intended use
• Data quality and sample selection
• Variable selection and segmentation
• Model methodology and assumptions
• Model implementation
• Ongoing performance monitoring
• Assess models developed using Logistic Regression, scorecards, Decision Trees, Random Forest, Gradient Boosting and XGBoost.
• Perform AUC/Gini, KS, PSI, calibration, back-testing, benchmarking, sensitivity, stress-testing and stability analysis.
• Evaluate model performance across vintages, score bands, credit-line bands, acquisition channels and customer segments.
• Investigate population drift, performance deterioration and areas of emerging risk.
• Compare development code and documentation with the production implementation to confirm that the model is working as intended.
• Review model limitations, monitoring thresholds, compensating controls and remediation plans.
• Prepare clear validation reports covering the observation, business impact, root cause, recommendation and severity.
• Support model inventory, risk classification, periodic monitoring and governance reporting.
• Present validation results to model developers, business stakeholders, senior management and partner banks.

Required Qualifications

• Bachelor's or Master's degree in Statistics, Mathematics, Economics, Engineering, Data Science, Finance or a related field.
• 2–5 years of experience in model development, model validation, model monitoring or credit-risk analytics.
• Hands-on experience with Python or SAS and SQL.
• Good understanding of credit-risk modelling, model performance, calibration and stability.
• Familiarity with vintage, delinquency, roll-rate and charge-off analysis.
• Ability to challenge model assumptions and explain technical findings in clear business language.
• Strong analytical, documentation and communication skills.

Preferred Experience

• Experience in US credit cards, consumer lending, subprime or near-prime portfolios.
• Experience with underwriting, application-risk, behaviour, collections or fraud models.
• Understanding of model-risk-management principles such as SR 11-7 and OCC guidance.
• Exposure to machine-learning explainability techniques such as SHAP and PDP.
• Familiarity with Redshift, Tableau, Git or cloud-based analytical environments.

What We Are Looking For

We need someone who is comfortable working independently, asking the right questions and going beyond simply calculating model-performance metrics. The successful candidate should be able to identify what is going wrong, explain why it matters to the business and recommend practical actions to address the risk.