Principal Data Scientist: Real-Time Fraud & Risk

Capital One National Association; McLean (VA); On-site; USD 162,000 - 185,000; Full time

Job summary

Capital One is seeking a Principal Associate Data Scientist in McLean, VA to advance debit transaction fraud data science with real-time decision systems. You will partner across teams to build predictive models and translate analytics into business impact.

The role emphasizes gradient boosting and large-scale data processing using Python, SQL, Spark, and Kubeflow/Kubernetes, delivering production-ready models and actionable insights for customers.

Qualifications

• Bachelor's degree in a quantitative field plus 5 years of data analytics experience
• Master’s degree in a quantitative field or MBA with quantitative concentration plus 3 years of data analytics experience
• PhD in a quantitative field
• Experience with machine learning for predictive tasks on large imbalanced datasets
• Experience with Python and SQL, Spark, and production-quality pipelines
• Experience with model backtesting and evaluation
• Experience coordinating data science projects in cross-functional teams

Responsibilities

• Partner with a cross‑functional team of data scientists, analysts, software engineers, and product managers to deliver a product that measurably keeps customers safe from fraudulent activities
• Leverage Python, Conda, AWS, H2O, Spark, SQL and more to reveal insights in large datasets
• Build machine learning models through all phases of development from design to deployment
• Translate complex analytics into tangible business goals

Skills

Python

SQL

Spark

AWS

H2O

XGBoost

LightGBM

Kubernetes

Kubeflow Pipelines

Education

Bachelor's degree + 5 years

Master's degree + 3 years

PhD in quantitative field

Tools

Conda

Job description

Capital One is seeking a Principal Associate Data Scientist in McLean, VA to advance debit transaction fraud data science with real-time decision systems. You will partner across teams to build predictive models and translate analytics into business impact.

The role emphasizes gradient boosting and large-scale data processing using Python, SQL, Spark, and Kubeflow/Kubernetes, delivering production-ready models and actionable insights for customers.