Back
Mid-level role in a metro with reasonable brand and some generalist ML skills, but credit specialization reduces density.
Role requires domain-specific credit/fraud modeling and bureau data knowledge, making cross-industry transferability low.
Explicit years, mandatory credit risk experience, and specific tooling (Python, PySpark, SAS, AWS) make filters strict.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Manage end-to-end lifecycle of credit and fraud models including development, evaluation, validation, monitoring, implementation testing, and documentation.
Lead model monitoring efforts, analyze model performance issues, and coordinate with stakeholders to implement action plans.
Own model risk management assessments, support validation and review processes, and collaborate with credit strategy teams on model usage and performance impact.
Bachelor's degree in quantitative field (Risk, Economics, Finance, Mathematics, Statistics, Engineering) with minimum 5+ years analytical/quantitative experience in consumer lending or 7+ years experience without degree.
Proficient in Python, Pyspark, SAS/SQL, Tableau, and AWS ML lifecycle tools.
Experience in end-to-end credit risk and fraud model development (application scorecards, transaction fraud detection).
Work Experience Required: Minimum 5+ years analytical/quantitative related to consumer lending (7+ years if no degree).
Experienced in managing credit models leveraging machine learning techniques like XGBoost, Random Forest, LightGBM, with strong understanding of model governance.
Capable of independently managing multiple stakeholders and projects globally, leading small teams with prioritization and mentoring focus.
Familiarity with US banking credit policies, model governance trends, and credit bureau data (FICO, Transunion, Equifax) and alternative data sources for enhanced modeling.