Sr. Director, Advanced Data Scientist

First National Bank•Omaha, NE

5d•$158,696 - $269,783•Onsite

About The Position

The Sr. Director, Advanced Data Scientist provides senior strategic and technical leadership for the Partnership Division's data science and modeling function. The role defines and executes a multi-year modeling roadmap and oversees the development and implementation of advanced machine learning models supporting credit decisioning and portfolio management. It combines quantitative expertise with executive-level influence to shape strategy, align cross-functional stakeholders, and deliver business impact. The position leads the design and development of advanced machine learning models for credit card acquisition, underwriting, account management, and customer risk. It owns model-development projects from problem definition through production implementation, including feature engineering, model selection and optimization, validation, documentation, and coordination with model validation and model risk management teams. The role also researches emerging machine learning methods and data sources, develops interpretable approaches suitable for regulatory and business needs, and establishes frameworks to monitor model performance and stability. As a technical leader and subject-matter expert, the incumbent sets modeling best practices, communicates strategy and results to senior leaders, and stays current with developments in machine learning, credit-risk analytics, and regulatory expectations. The role is anticipated to be onsite at the posted location; work location may change based on business needs.

Requirements

Master's degree or PhD in Statistics, Data Science, Computer Science, Mathematics, Operations Research, Econometrics, or a related quantitative field.
At least 7 years of experience developing statistical or machine learning models.
Strong experience independently developing predictive models using large and complex datasets.
Demonstrated expertise in Python and/or R and strong SQL skills.
Experience with gradient boosting, XGBoost or LightGBM, ensemble methods, neural networks, and other advanced machine learning techniques.
Experience with model explainability techniques such as SHAP and partial dependence.
Experience with the full model-development lifecycle, including development, implementation, and monitoring.
Strong understanding of credit-risk concepts and consumer lending.
Unrestricted work authorization; must not require future sponsorship.

Nice To Haves

PhD, particularly with strong research experience in machine learning, statistics, or quantitative finance.
Experience developing models in financial services or consumer credit, especially credit card acquisition and account-management models.

Responsibilities

Define and own the multi-year modeling roadmap for custom credit-risk acquisition and portfolio management models, including priorities, sequencing, and investment rationale.
Lead discussions with business, credit risk, first-line risk, compliance, and technology stakeholders to align modeling methodology, priorities, and risk considerations.
Identify and evaluate emerging modeling capabilities, analytical approaches, and implementation methods.
Communicate modeling strategy, project status, and results to senior leaders in clear, executive-ready reporting that translates quantitative findings into business insights.
Independently design and develop advanced machine learning models for credit card acquisition, underwriting, account management, and customer risk.
Apply statistical and machine learning techniques to large-scale customer and credit datasets, including gradient boosting, random forests, neural networks, generalized additive models, ensemble methods, and survival models.
Conduct fair lending analysis, including least discriminatory analysis.
Identify opportunities to improve model performance, stability, interpretability, and business value.
Lead model-development projects end to end, from problem definition through production implementation.
Translate business objectives into modeling frameworks, target variables, populations, and performance criteria.
Perform feature engineering, variable selection, model development, hyperparameter optimization, and performance evaluation.
Establish training, validation, and out-of-time testing strategies.
Document modeling methodology, assumptions, limitations, and results.
Partner with model validation and model risk management teams to address challenges and incorporate feedback.
Research emerging machine learning techniques and evaluate their applicability to credit risk.
Develop approaches for extracting predictive signals from traditional and alternative data sources.
Investigate nonlinear relationships, interactions, customer behavior patterns, and temporal dynamics.
Develop interpretable machine learning approaches that balance predictive performance with regulatory and business requirements.
Explore explainable AI, causal modeling, ensemble learning, semi-supervised learning, and automated machine learning where appropriate.
Develop model performance and stability monitoring frameworks.
Monitor predictive performance, population shifts, variable stability, and model degradation.
Identify emerging risks and recommend model recalibration, redevelopment, or replacement when appropriate.
Conduct ongoing research to improve model performance and robustness.
Serve as a subject-matter expert in advanced machine learning and credit-risk modeling.
Establish best practices for model development, testing, documentation, and deployment.
Stay current with advances in machine learning, credit-risk analytics, and regulatory expectations.