Data Scientist

Remote (United States)

Job Details

Location: United States

Workplace: Remote

Employment Type: Full-Time

Experience: 4+ years of applied statistical analysis and predictive modeling experience

Core Areas: Predictive Modeling, Causal Inference, Anomaly Detection, Regression Analysis, Python or R, SQL, Model Validation, Feature Importance Analysis

Compensation: $155,000 – $175,000 per year

About the Role

This opportunity is for a Data Scientist who will lead advanced research and predictive modeling using large-scale residential housing and energy performance data. The position focuses on causal inference, anomaly detection, model validation, and predictive accuracy, with responsibility for identifying relationships across complex real-world datasets and developing new performance metrics.

The role requires strong statistical expertise, proficiency in Python or R and SQL, and experience validating analytical models against field-collected or ground-truth data. The Data Scientist will also serve as the primary technical contact for external research and statistical partners and contribute to white papers, research briefs, and other publications.

What You'll Do

Research and Causal Inference

• Manage research conducted with external consultants and statistical firms to identify correlations and causal relationships between home performance data and other housing-related data, including energy cost and mortgage performance.
• Apply regression analysis, propensity score matching, and, where data permit, instrumental variable methods to evaluate causal relationships.
• Ensure causal claims are supported by appropriate causal inference methods rather than inferred from controlled regression alone.

Anomaly Detection and Model Validation

• Analyze approximately 92 million residential SCOREs and energy models to identify homes where the SCORE or model output may not accurately reflect actual physical configuration or energy consumption.
• Use anomaly detection, outlier analysis, and validation against field-collected home characteristics to evaluate model accuracy.

Predictive Model Improvement

• Analyze modeled energy consumption, home physical characteristics, and utility billing data to identify and implement improvements to predictive accuracy.
• Analyze relationships between field-collected home performance characteristics and SCORE outputs to identify opportunities to improve SCORE accuracy.
• Use feature importance analysis and comparisons against field-validated benchmarks to evaluate model performance and identify improvement opportunities.

New Metrics and Climate Risk

• Support the development of new performance metrics, including Total Cost of Ownership, by identifying and validating relevant data sources and analytical approaches.
• Evaluate opportunities to integrate climate risk data into performance models to improve predictive precision related to home climate vulnerability.
• Analyze relationships between home resilience features and the ability to withstand extreme climate events.

External Research Partnerships and Publications

• Serve as the primary technical point of contact for external data and statistical partners.
• Assist with authoring white papers, briefs, and other publications documenting research findings for research pages, academic journals, and other appropriate outlets.

Qualifications

Required Experience

• 4+ years of applied experience in statistical analysis and predictive modeling, ideally involving large, real-world, non-experimental datasets.
• Hands-on experience with causal inference methods, including regression analysis, propensity score matching, and instrumental variable approaches.
• Experience applying anomaly detection and outlier analysis techniques to large datasets.
• Experience validating model outputs against ground-truth or field-collected data.
• Experience working directly with external consultants, research firms, or academic partners on collaborative analytical projects.

Required Skills

• Strong understanding of when correlation-based methods are and are not sufficient to support causal claims.
• Strong proficiency in Python or R for statistical and analytical programming.
• Strong proficiency in SQL.
• Ability to translate statistical findings into clear, non-technical explanations for internal stakeholders and external partners.

Education

• Master's degree in Statistics, Economics, Data Science, Applied Mathematics, or a related quantitative field, or equivalent experience.

Preferred Qualifications

• Experience with feature importance analysis and model interpretability techniques.
• Familiarity with housing, real estate, energy, or utility data, including assessor records, permit data, utility billing, and energy modeling.
• Experience integrating or evaluating climate or environmental risk data in predictive models.
• A track record of authoring or co-authoring published research.
• Experience working with ambiguity and scale, including large datasets, real-world conditions, and innovative analytical methodologies.
• Comfort working semi-independently with support from partners and collaborators.

Benefits

• Medical, vision, and dental coverage provided at no cost for employees and their families, with an option to purchase upgraded coverage at minimal employee cost.
• Flexible Spending Account, Health Savings Account, and dependent care account options.
• Life insurance coverage.
• Employer-paid cell phone service.
• 401(k) plan with employer matching up to 4%.
• Stock options.
• 15 vacation days per calendar year.
• Paid holidays, including the week between Christmas and New Year's Day.
• Floating holiday for the employee's birthday.
• Paid sick leave and parental leave.
• Flexible work environment with remote work available from anywhere within the United States.