Senior Manager of Machine Learning

Kafene

1d•Remote

About The Position

Kafene is revolutionizing the lease-to-own space. We're the point-of-sale powerhouse making flexible lease-to-own accessible to everyone—prime and non-prime customers alike. Our secret weapon? Cutting-edge AI and machine learning that analyzes 20,000+ data inputs in real-time, empowering retailers across furniture, appliances, electronics, tires, and durable goods to say "yes" to more customers. The numbers tell our story: over $500 million in sales and counting. But we're just getting started. Our 150-person team spans NYC headquarters, Wilmington, and remote talent across the globe—all united by a culture that thrives on collaboration, innovation, and genuine support. We don't just talk about great workplace culture; we deliver it. That's why Built In named us a Startup to Watch and Forbes recognized us as one of the Best Startup Employers. Ready to be part of the fintech revolution? Join us. Credit and risk are at the heart of our business. We're looking for a Senior Manager of Machine Learning Engineering — a senior individual contributor who will own the full lifecycle of the ML models that power our credit risk decisions. Reporting directly to the VP of Risk, you'll design, build, deploy, and monitor the models that determine how we approve customers, set credit amounts, predict defaults, and forecast losses. You'll work closely with cross-functional partners across risk, engineering, finance, and sales — and you'll have the rare opportunity to shape both the technical infrastructure and the business strategy behind it.

Requirements

Master's or PhD in a quantitative discipline (Data Science, Statistics, Mathematics, Computer Science, Engineering, or related field) preferred
5+ years of hands-on experience as a Data Scientist or Machine Learning Engineer, with a strong track record of building and deploying models in credit risk, fraud detection, or financial analytics
Advanced Python proficiency with demonstrated experience building production-grade ML models
Strong SQL skills for data querying and manipulation
Deep knowledge of ML algorithms including gradient boosting, ensemble methods, regression models, decision trees, and AutoML frameworks
Prior experience in lending, fintech, or financial services is highly preferred
Familiarity with model risk governance frameworks and experience working with validation teams is a plus
Able to translate complex technical concepts clearly for both technical peers and executive stakeholders

Responsibilities

Feature Engineering: Analyze internal and external datasets to surface trends and build high-signal features — including Debt-to-Income (DTI), Payment-to-Income (PTI), payment behavior patterns, and account balance signals — that improve the accuracy and predictive power of our credit models.
Model Development: Design and develop strategic ML models end-to-end, including approval amount sensitivity models that optimize credit line assignment strategies and drive measurable business outcomes.
Data Preparation: Manipulate, clean, and transform structured and unstructured data to ensure quality and readiness for modeling. Uphold rigorous standards for data integrity throughout the pipeline.
Vendor Evaluation: Partner with external data vendors to assess third-party data products and scoring solutions. Lead cost-benefit analyses to guide partnership decisions and data integration strategies.
Research & Innovation: Stay at the forefront of machine learning and feature engineering advances. Continuously incorporate new techniques to improve model performance and push the quality of our credit risk systems forward.
Model Implementation & Validation: Collaborate with technology and engineering teams to implement and validate models with precision. Identify opportunities to improve the speed, accuracy, and repeatability of model deployment.
Monitoring & Maintenance: Proactively track model performance in production. Lead calibration and redevelopment efforts to keep models accurate, reliable, and aligned with evolving business conditions.
Compliance & Governance: Ensure all models meet regulatory standards and data vendor usage policies. Maintain thorough documentation of development processes, methodologies, and validation procedures. Support internal and external audit processes as needed.
Cross-Functional Partnership: Work closely with risk management, engineering, finance, and sales to translate business challenges into scalable, data-driven solutions — and ensure seamless integration of models into the broader risk management framework.