Design, build, validate, deploy, and monitor ML models (credit risk, fraud, transaction timing). Create training datasets, run A/B tests, analyze customer behavior, and collaborate with Engineering, Product, and Analytics to deliver end-to-end data science solutions.

Lead and own end-to-end ML modeling for underwriting, fraud, and payments: build, validate, deploy, monitor models; create training datasets; run A/B tests; analyze customer trends; establish feature and model best practices; and mentor junior data scientists while collaborating with Engineering, Product, and Business teams.

Lead and grow a data science team to build predictive models for credit risk and payments; mentor scientists; integrate DS work with product, engineering, and operations; run quarterly planning with stakeholders; drive adoption of AI-assisted and agentic workflows with validation and quality standards; and collaborate with modeling engineering to improve model research, development, and deployment infrastructure.