Design, develop and deploy advanced statistical or machine learning models related to credit risk, pricing, collections, fraud, and other high-impact business use cases that drive better data-driven decisions
Execute the full model lifecycle, from initial data discovery and feature engineering to deployment, monitoring and iterative improvement
Partner with cross-functional teams including Portfolio Strategy, Collections, Engineering, Product, Underwriting, and Sales to integrate models into our applications and ensure they function seamlessly
Communicate complex technical concepts, model results, and business implications to both technical and non-technical stakeholders
Develop production-grade code and contribute to internal toolkits, documentation, and peer code review to ensure high-quality delivery
Build and maintain production machine learning pipelines and monitoring systems to ensure models are reliable, scalable and continuously improving

5+ years of hands-on model development and deployment experience using advanced statistical and machine learning techniques such as generalized linear models, gradient boosting and deep learning
Experience in fintech or financial services, specifically building Collections models, is highly preferred.
Proficient in Python, SQL and Git
Experience with workflow orchestration tools, such as Metaflow
Experience deploying and managing models within a cloud platform (AWS, Sagemaker)
Strong foundation in statistics and machine learning, and knowledge of experimental design
Excellent communication skills
Strong critical thinking and problem-solving ability
Nice to have experience: cloud data warehouses (e.g. Snowflake, Databricks), Metaflow, Arize, Sagemaker, decision engines (e.g. Taktile), feature stores (e.g. Tecton)
Bachelor's degree in Financial/Applied Math, Operations Research, Economics, and/or Statistics. Masters/PhD is a plus.

Senior Data Scientist

Key skills