Risk Management, Wholesale Quantitative Research, Associate

What you'll do

• Develop wholesale credit risk measurement models for portfolios like Commercial Real Estate and structured products.
• Build credit loss models to support the bank’s Current Expected Credit Loss estimations.
• Develop stress testing models to support Comprehensive Capital Analysis and Review processes.
• Design efficient numerical methods and high-performance computing solutions for model estimation and calibration.
• Build reusable analytics software frameworks and integrate model outputs into downstream systems.
• Analyze large datasets to derive insights that improve model accuracy and stability.
• Assess model performance and limitations to identify and monitor model risk.
• Communicate methodology, results, and limitations to model governance committees and regulators.

What we're looking for

• Master’s degree or higher in a quantitative discipline such as mathematics, physics, statistics, economics, finance, or computer science.
• 3 years of experience developing statistical and/or economic models in a financial services or risk context.
• 3 years of experience applying regression and multivariate statistical techniques to real-world datasets.
• 3 years of hands-on programming experience in Python for data analysis and modeling, including pandas and NumPy.
• 2 years of experience working with machine learning techniques in model development or analytics workflows.
• Demonstrated experience working with large datasets and building repeatable data pipelines for modeling.
• Knowledge of core banking risks and how risk is measured and managed in a wholesale credit context.
• Ability to explain complex quantitative concepts to non-technical stakeholders in clear, concise language.
• Doctorate in a quantitative discipline (preferred).
• Experience developing wholesale credit risk models for Basel, CCAR, or CECL exercises (preferred).
• Experience designing numerical algorithms for model calibration (preferred).
• Experience with Linux or Unix environments for research and production workflows (preferred).
• Familiarity with cloud platforms and model lifecycle tooling such as AWS, Azure, MLflow, Kubeflow, or SageMaker (preferred).
• Experience using modern artificial intelligence tools to accelerate model development, testing, or documentation workflows (preferred).
• Knowledge of graph or network analytics for counterparty or contagion risk modeling (preferred).