• Partner with Product, Engineering, and other stakeholders to translate ambiguous business challenges into well-defined data science problems • Own the end-to-end lifecycle of data science models, from data exploration and feature engineering to deployment, monitoring, and continuous improvement in production • Develop robust, scalable, and efficient models, thoughtfully balancing algorithmic complexity against interpretability, business needs, and delivery timelines • Examples of data science initiatives include: using NLP/LLMs to classify transactions into standardized categories, training gradient boosting trees to predict loan default probability and loss-given-default based on transactional data, and building an entity resolution system to match financial documents across time with a specific borrower