Fraud Analytics Lead (Remote)

Affirm, Inc.; Phoenix (AZ); Remote; USD 164,000 - 224,000; Full time

Benefits offered by this job

Health coverage

ESPP

Tech stipends

Flexible time off

Job summary

Affirm, Inc. seeks an experienced Analytics Lead to own fraud performance for depository products. You will monitor losses, approvals, false positives, and customer friction while shaping risk strategy and data-driven decision making.

Collaborating with Product, Engineering, ML, and Fraud Operations, you will build scalable data models, dashboards, and scorecards. The role requires 7+ years of analytics and fluency in SQL and Python, with a bias toward practical risk optimization.

Qualifications

• 7+ years of analytics experience.
• Fluent in SQL and Python.
• Ability to collaborate across many teams and influence decisions.
• Strong communication of findings to technical and non-technical audiences.
• Demonstrated execution in fast-paced environments.
• Knowledge of risk management and fraud principles is preferred.

Responsibilities

• Own fraud performance for depository products, monitoring losses, approvals, false positives, and customer friction.
• Build and maintain scalable data models and transformation pipelines (e.g., DBT) for depository data.
• Develop dashboards, scorecards, and monitoring frameworks for fraud performance and portfolio health.
• Lead testing and evaluation of fraud strategy changes and cross-functional partnerships to improve risk controls.

Skills

Analytics experience

SQL

Python

Collaboration

Communication

Job description

Affirm, Inc. seeks an experienced Analytics Lead to own fraud performance for depository products. You will monitor losses, approvals, false positives, and customer friction while shaping risk strategy and data-driven decision making.

Collaborating with Product, Engineering, ML, and Fraud Operations, you will build scalable data models, dashboards, and scorecards. The role requires 7+ years of analytics and fluency in SQL and Python, with a bias toward practical risk optimization.