
Overview
Position Summary:
We’re seeking a Data Scientist to support the development and deployment of machine learning models and analytics solutions that improve decision-making across the mortgage lifecycle—from acquisition to servicing. In this hands-on role, you’ll contribute to building predictive models, customer segmentation tools, and automation workflows that enhance operational efficiency and customer outcomes. You’ll work closely with senior data scientists and cross-functional teams to translate business needs into well-scoped modeling tasks, with opportunities to apply natural language processing (NLP), statistical modeling, and experimentation frameworks in a regulated financial environment. This role reports to a senior leader in Data Science.
Job Functions and Responsibilities:
- Develop and maintain machine learning models and statistical tools for use cases such as risk scoring, churn prediction, segmentation, and document classification.
- Collaborate with Product, Engineering, and Analytics teams to identify data-driven opportunities and support automation initiatives.
- Translate business questions into modeling tasks and contribute to the design of experiments and success metrics.
- Assist in building and maintaining data pipelines and model deployment workflows in partnership with data engineering.
- Apply techniques such as supervised learning, clustering, and basic NLP to structured and semi-structured mortgage data.
- Support model monitoring, performance tracking, and documentation to ensure compliance and audit readiness.
- Contribute to internal best practices and participate in peer reviews and knowledge-sharing sessions.
- Stay current with developments in machine learning and analytics relevant to mortgage and financial services.
Qualifications:
- Minimum education required: Masters or PhD in engineering/math/statistics/economics, or a related field
- Minimum years of experience required: 2 (or 1, post-PhD), ideally in mortgage, fintech, or financial services
- Required certifications: None
- Specific skill or ability needed
- Minimum software or applications experience required/preferred
- Minimum experience required using mobile technology: None
- Any other requirements an ideal applicant needs to have that is not covered by above: None
- Experience working with structured and semi-structured data; exposure to NLP or document classification is a plus.
- Understanding of model development lifecycle, including training, validation, and deployment.
- Familiarity with data privacy and compliance considerations (e.g., ECOA, CCPA, GDPR) is preferred.
- Strong communication skills and ability to present findings to technical and non-technical audiences.
- Proficiency in Python (e.g., scikit-learn, pandas), SQL, and familiarity with ML frameworks like TensorFlow or PyTorch.