Build, improve, and maintain ML models for personalizing the user experience including on-demand pay balance optimization, content personalization, and fraud controls.
Build reliable data pipelines and features for model development, following team infrastructure standards. Identify gaps in data infrastructure along the way and advocate for solutions with engineering partners.
Develop, evaluate, deploy, monitor, and improve both batch and real time models following established production standards.
Stay current on AI/ML developments and apply sound judgment in algorithm selection and technique adoption by evaluating tradeoffs across modeling approaches and recommending the best tool for the problem.
Write clean, well-documented, traceable, versioned, and reproducible code across all model development and pipeline work, following team standards for maintainability and auditability.
Follow and contribute to data quality standards and validation practices; flag issues proactively and help improve team patterns.
Partner with product and engineering on scoped problem areas, translating defined business questions into well-structured DS solutions. Bring senior DS leadership in early on ambiguous or high-stakes problem framing.
Communicate model results and tradeoffs clearly to product and cross-functional partners, connecting technical outputs to business outcomes.
Requirements
5+ years of Data Science & Machine Learning experience within fintech, payments, or a similarly regulated consumer domain.
Bachelor’s or advanced degree in a quantitative discipline (e.g., computer science, machine learning, statistics, data science).
Track record of independently building models that drive measurable business outcomes;
Experience building and maintaining reliable feature engineering pipelines, with advanced SQL and Python skills and a working knowledge of the data infrastructure that supports model development at scale.
Hands on experience with end-to-end model deployment; data pipelines, model monitoring, drift detection, and A/B test execution, with a strong instinct for production reliability.
Experience owning models in production environments where failures have real financial or compliance consequences.
Strong proficiency across modern AI, classical ML, statistical, and probabilistic methods.