Senior Director, Credit Risk ML & Modeling

FNBO; Minnesota; Hybrid; USD 159,000 - 270,000; Full time

Benefits offered by this job

Medical Insurance

Dental Insurance

Vision Insurance

401k with match

Time Off

HSA/Dependent Care

Employee Banking

Growth Opportunities

Tuition Assistance

Disability Insurance

Job summary

FNBO is seeking a Sr. Director, Advanced Data Scientist to lead the data science and modeling function within the Partnership Division.

You will define a multi-year modeling roadmap, guide the development of credit risk models, and partner with risk, compliance and technology teams to deliver measurable business impact. You will independently own model development from problem framing to production, applying cutting-edge ML methods while addressing fairness, explainability, and regulatory

Qualifications

• Master's degree or PhD in Statistics, Data Science, CS, Mathematics, OR Economics/OR Quant Finance.

Responsibilities

• Define multi-year modeling roadmap for credit risk acquisition and portfolio management.
• Lead discussions with senior stakeholders to align methodologies and risk considerations.
• Independently design and develop advanced ML models for credit decisions and portfolio management.
• Apply advanced ML techniques to large-scale datasets and evaluate algorithms.
• Establish training, validation and out-of-time testing strategies.

Skills

Python

R

SQL

XGBoost

LightGBM

Neural networks

Explainable AI

Education

Master's degree in a quantitative field

PhD preferred in ML/stats/quant finance

Tools

SHAP

Partial dependence

Job description

FNBO is seeking a Sr. Director, Advanced Data Scientist to lead the data science and modeling function within the Partnership Division.

You will define a multi-year modeling roadmap, guide the development of credit risk models, and partner with risk, compliance and technology teams to deliver measurable business impact. You will independently own model development from problem framing to production, applying cutting-edge ML methods while addressing fairness, explainability, and regulatory