Lead Data Scientist

Financial or risk modeling experience within a regulated industry is required, including direct experience defending models during external audits. Formal people management experience is not required., * Eight or more years of experience in data science, predictive analytics, quantitative analysis, or advanced risk modeling. \n

• Financial or risk modeling experience within a regulated industry. \n

• Direct experience supporting external model audits and defending model methodology and results. \n

• Advanced Python and SQL proficiency, including at least three years of experience developing models in Python and writing complex SQL queries. \n

• Experience with gradient boosting models, including XGBoost or CatBoost. \n

• Strong mathematical and statistical knowledge, including probability, sampling, predictive modeling, and model validation. \n

• Experience working with financial or credit datasets and translating findings into measurable business outcomes. \n

• Demonstrated ability to independently deliver projects from initial problem definition through implementation. \n

• Strong presentation skills, including experience communicating technical findings to executive audiences. \n

• A bachelor’s degree in mathematics, statistics, economics, computer science, quantitative engineering, or a related discipline with substantial mathematical and statistical coursework. \n, Relevant experience may include credit risk, credit loss assessment, probability of default modeling, scorecards, payment behavior, credit attributes, mortgages, credit cards, banking, or credit bureau data., * A master’s degree in data science or another quantitative discipline. A business analytics master’s degree alone does not replace the required mathematical and statistical foundation. \n

• Experience with portfolio risk management, loan scoring, or quantitative analysis of capital assets. \n

• Familiarity with model risk management practices and SR 11-7 guidelines. \n

• Experience with Snowflake and AWS services, including Amazon S3. \n

• Experience applying predictive analytics to residential real estate or related operational decisions., Applicants must be authorized to work in the United States without employer sponsorship now or in the future.

n \n

• Own analytical projects from stakeholder intake and scoping through data preparation, model development, validation, implementation, and monitoring. \n

• Develop models supporting payment behavior, collectability, resident renewals, renovation costs, and repair decisions. \n

• Apply gradient boosting, regression, segmentation, and other statistical and machine learning methods to financial, credit, and operational datasets. \n

• Gather, reconcile, clean, and validate data from internal and external sources. \n

• Evaluate model assumptions, conduct backtesting, and document methodologies, limitations, and results. \n

• Defend model design, assumptions, and validation approaches during external audits. \n

• Translate analytical findings into financial impact, including cost savings, revenue opportunities, and changes in risk exposure. \n

• Present recommendations and business cases to senior leaders and executive stakeholders. \n

• Partner with business teams to implement solutions and measure ongoing performance. \n

• Mentor junior colleagues on analytical methods, project structure, and model development. \n

\n

\n

Data science supports decisions across the business, including improving occupancy and resident retention, assessing payment behavior, and forecasting property expenses. The analytics team works directly with leadership to identify financial opportunities, quantify their value, and implement solutions that deliver measurable results.