Credit Model Developer

About the role

Support the Credit Risk Models Team with the development, testing, implementation, monitoring, documentation, and maintenance of all credit risk models. These models are used for a variety of activities, including: CECL, stress testing, loss forecasting, origination, portfolio management, and economic capital.

Responsibilities

• Sourcing, cleaning, and transforming data
• Researching applicable methods
• Training and testing a variety of specifications
• Documenting all facets of the development process
• Implementing models and related logic in production systems
• Auditing and validating model outputs across different levels of inputs
• Communicating aspects of the model and its application to non-technical stakeholders

Qualifications

• PhD or Master’s degree in Statistics, Econometrics, Mathematics or related quantitative field
• Bachelor’s degree in a quantitative field with additional certifications or experience may be considered
• Minimum 3 years of model development or validation experience
• Advanced quantitative statistical modeling skills (Regression, Time Series, Survival Analysis, Markov Chain, etc.)
• Experience with Python and SQL
• Strong analytical and critical thinking skills with high attention to detail and accuracy
• Excellent verbal, written, and interpersonal communication skills

Preferred Experience

• 5 or more years of model development or validation experience, particularly in credit risk or stress testing
• Working knowledge of Python, R, SAS, and SQL
• Knowledge of Git-based machine learning operations practices in the cloud (MLOps)
• Working knowledge of Generally Accepted Accounting Principles (GAAP), Basel III, Dodd-Frank Act Stress Testing, CCAR, and bank accounting/regulatory reporting requirements
• Ability to clearly articulate, in writing or orally, ideas, analytic insights, and recommendations to both technical and non-technical audiences, including an executive audience
• Ability to use advanced statistical and mathematical software to perform descriptive, predictive, and prescriptive analysis leveraging a variety of statistical techniques (such as segmentation, logistic regression, sensitivity analysis, and machine learning)
• An ability to identify key problems, conduct in-depth research, and articulate well-reasoned solutions