Analyst - Wholesale Credit Risk Quantitative Research

Role overview

Modeling and monitoring

• Design and develop loss forecasting models for regulatory purposes.
• Conduct back-testing, performance monitoring, and annual model reviews in line with model governance standards.
• Use statistical and econometric techniques, and machine learning where appropriate, for forecasting, risk monitoring, and model explainability.

Data, implementation, and reporting

• Clean and filter large panel datasets and engineer features.
• Partner with Data and Technology teams to implement models with robust data pipelines and controls.
• Prepare comprehensive model documentation and support communication of results and model impacts for internal, regulatory, and senior stakeholder review.

Required qualifications and skills

• Degree in Engineering, Financial Engineering, Computer Science, Mathematics, Sciences, Statistics, Econometrics, or another quantitative field.
• Strong background in calculus, linear algebra, probability, and statistics.
• Practical and theoretical knowledge of generalized linear models, time-series analysis, clustering, decision trees, and logistic regression.
• Experience handling large panel datasets, including cleaning and filtering.
• Proficiency in an object-oriented programming language and Python or C++, with version control, testing, and reproducibility practices.
• Creative problem-solving, eagerness to learn credit risk and regulatory and accounting concepts, and strong written and verbal communication.

Preferred qualifications

• Two or more years of relevant experience; wholesale credit product knowledge and regulatory loss-forecasting model experience are preferred.
• Knowledge of securitization products such as RMBS, ABS, and CLOs is preferred.
• Knowledge of bond and loan pricing, other financial products or asset classes, options pricing theory, or financial regulations is preferred.
• Machine learning and generative AI experience; familiarity with SQL, distributed data tools, cloud workflows, or high-performance computing; and collaborative internal partnerships are preferred.

About the employer and team