Staff Machine Learning Engineer (ML Portfolio)

Affirm, a pioneering fintech company, is seeking a Staff Machine Learning Engineer to join their Portfolio ML team within the Decisions Foundations organization. This role presents an exciting opportunity to work at the intersection of machine learning and financial technology, helping to revolutionize the credit industry through honest and consumer-friendly solutions.

The Portfolio ML team plays a crucial role in managing and optimizing loan opportunities across Affirm's properties. They develop sophisticated models and tools for portfolio management that balance unit economics, product growth, and user experience. The team's work encompasses ROA-based decisioning, real-time conversion rate prediction, counterfactual portfolio simulation, and loan valuation.

As a Staff Machine Learning Engineer, you'll be responsible for setting technical strategy and leading critical, business-impacting projects. The role requires expertise in machine learning techniques such as Generalized Linear Models, Gradient Boosting, Deep Learning, and Probabilistic Calibration. Domain knowledge in credit risk and portfolio management is valued, though not required.

The position offers a competitive compensation package, including a base salary range of $200,000 - $275,000 (depending on location), equity rewards, and comprehensive benefits including fully covered medical insurance for employees and dependents. Affirm embraces a remote-first culture, offering flexibility and work-life balance while maintaining high standards of collaboration and technical excellence.

This role is ideal for an experienced engineer who excels in both technical leadership and cross-functional collaboration. You'll have the opportunity to shape the future of financial technology while working with cutting-edge machine learning applications in a mission-driven environment. The position requires strong communication skills and the ability to mentor team members while driving technical excellence and operational efficiency.