The Director, Data Science – Credit Risk & AI leads the Credit Strategy data science function and is responsible for advancing the organization’s capabilities across underwriting, credit risk modeling, loss forecasting, fraud and risk analytics, model governance, and AI-enabled analytical innovation.

This leader owns the data science and model development roadmap, leads and develops data science talent, and partners closely with Credit Strategy, Risk, Compliance, IT, Data Engineering, Operations, and external data providers. The Director ensures models and analytical solutions are scalable, production-ready, well governed, and aligned with the organization’s risk appetite and profitable growth objectives.

Essential Functions

Own and execute the credit risk data science roadmap across underwriting, default and delinquency risk, fraud, profitability, portfolio performance, and loss forecasting.
Lead and prioritize model development initiatives throughout the full model lifecycle, including design, development, validation, deployment, monitoring, and ongoing performance management.
Lead, coach, and develop data science talent by establishing technical standards, reviewing analytical approaches, providing mentorship, and ensuring consistent, high-quality execution.
Establish and maintain model development standards, documentation requirements, governance routines, and monitoring frameworks for credit decisioning and risk models.
Partner with Credit Strategy leadership to translate business objectives into analytical strategies that improve credit decision quality, portfolio performance, profitability, and operational efficiency.
Guide the application of machine learning, statistical modeling, regression, segmentation, champion/challenger testing, and experimental frameworks to evaluate and optimize credit policies and model changes.
Oversee the development of scalable modeling datasets, feature pipelines, and analytical environments that support production decisioning, model development, and experimentation.
Collaborate with Data Engineering, IT, Risk, Compliance, Operations, and external data providers to deploy, maintain, and enhance production models and decisioning capabilities.
Establish processes to monitor model performance, drift, stability, and business outcomes, and lead remediation or enhancement efforts when performance changes.
Communicate model strategy, performance, risks, tradeoffs, and recommendations to senior leadership, governance forums, and cross-functional stakeholders.
Lead the responsible adoption of modern AI and AI-assisted tools to improve analytical productivity, model development, documentation, governance reporting, and knowledge sharing.
Ensure models and analytical work are appropriately documented and prepared to support independent validation, audit, compliance, and regulatory review.
Stay current on emerging methodologies, technologies, data sources, and industry practices related to consumer credit risk, data science, machine learning, and artificial intelligence.

Required Education and Experience

Bachelor’s degree in Mathematics, Statistics, Engineering, Computer Science, Data Science, or another quantitative STEM discipline, or commensurate work experience required
7 years of experience in consumer lending, fintech, banking, credit risk analytics, data science, or related quantitative field.
3 years of experience leading data science, credit risk modeling, advanced analytics, or model governance initiatives, including demonstrated leadership of technical talent and/or complex analytical programs.
Demonstrated experience developing, deploying, monitoring, and governing models supporting underwriting, credit risk, fraud, profitability, portfolio management, or loss forecasting.
Advanced proficiency with SQL and Python and strong knowledge of machine learning, statistical modeling, and production model lifecycle management.
Strong understanding of model development documentation, monitoring, independent validation, audit, governance, and regulatory expectations within a lending or financial services environment.
Demonstrated ability to translate business problems into analytical solutions and evaluate model performance in the context of both risk and financial outcomes.
Proven ability to lead complex, cross-functional initiatives involving Credit, Risk, Compliance, IT, Data Engineering, Operations, and external partners.
Strong executive communication and influencing skills, with the ability to translate complex analytical concepts and model outputs into clear business insights, risks, tradeoffs, and recommendations.

Director, Data Science – Credit Risk & AI at Aqua Finance