Remote Senior Data Scientist

Job Description

We are seeking a Senior Data Scientist who will join our Enterprise Healthcare Client's Excalibur team. This team builds the enterprise data platform behind the company's Digital Employee Experience (DEX) Score, a composite measure of how well colleague devices and applications are actually performing. Version 1 of the score was fit on a single month of data with component weights set by expert judgment. The team is now rebuilding it as DEX Score 2.0 on a dataset spanning more than a year of endpoint telemetry across over 100,000 Windows devices. The core problem is a statistical one. The current score correlates strongly with technical performance metrics such as response time, but only weakly with what colleagues report actually feeling, where wait time and productivity loss matter most. We are looking for a Senior Data Scientist to own the methodology that closes that gap: rigorous correlation and regression studies, principled weighting, sound temporal validation, and a scoring model that stands up to scrutiny from application owners, governance, and leadership. This is a hands on modeling role with high visibility. Your work determines how the enterprise measures and prioritizes digital experience for its workforce. Day-to-day responsibilities will include:

• Lead the methodology. Own the statistical design of DEX Score 2.0, including component selection, scoring functions, weighting, and the Good to Bad segment thresholds.
• Quantify what colleagues feel. Design and run correlation and regression studies relating telemetry components (crashes, errors, hang time, wait time, response time, page load time, productivity loss) to colleague reported experience.
• Develop and compare models. Fit and compare candidate models (regularized regression, mixed effects, factor and principal component approaches, optimization based weighting) and defend the choice with evidence.
• Validate properly over time. Move validation from a single month to out of time holdouts, drift and seasonality analysis, and stability testing across the full multi year dataset.
• Resolve the ground truth question. Determine whether survey sentiment should serve as a composite input or as a calibration label, and design the validation study against real users.
• Evaluate persona and threshold decisions. Test whether scoring should flex by persona (for example, contact center versus engineering) and whether current segment bands still hold against today's fleet.
• Partner on data. Build features from Aternity, Tanium, Zscaler, Teams, and Outlook telemetry on Databricks alongside Excalibur data engineers. Communicate and document. Produce version controlled, reproducible methodology documentation and translate results into clear weight and threshold recommendations for Digital Workplace stakeholders and executive leadership.

Skills and Requirements

• MS or PhD in Statistics, Mathematics, Econometrics, Computer Science, or a related quantitative field, or a BS with equivalent applied experience.

• 5+ years developing, validating, and deploying statistical and machine learning models in production.

• Deep expertise in regression analysis (linear, logistic, regularized, mixed effects), correlation analysis, hypothesis testing, and experimental design.

• Experience constructing composite indices or scorecards, including weighting methods, normalization and scaling, and sensitivity analysis.

• Strong command of model validation: cross validation, temporal and out of time validation, calibration, and bias versus variance tradeoffs.

• Experience with time series and longitudinal data, including drift, seasonality, and panel structures.

• Expert Python (pandas, statsmodels, scikit-learn, SciPy) and SQL, with experience on large datasets in Databricks or Spark. Strong documentation, reporting, and presentation skills: you write clear methodology documents, build reports and dashboards that stakeholders trust, and present statistical findings to executive audiences in a way that drives decisions.

• Survey methodology or psychometrics: measurement validity, reliability, and latent construct modeling.

• Causal inference methods such as difference in differences, matching, or instrumental variables.

• Bayesian modeling and uncertainty quantification.

• Familiarity with endpoint or digital experience monitoring data (Aternity, Tanium, Zscaler, or similar). Azure, Databricks Unity Catalog, and modern data platform tooling.

We are a company committed to creating diverse and inclusive environments where people can bring their full, authentic selves to work every day. We are an equal employment opportunity/affirmative action employer that believes everyone matters. Qualified candidates will receive consideration for employment without regard to race, color, ethnicity, religion, sex (including pregnancy), sexual orientation, gender identity and expression, marital status, national origin, ancestry, genetic factors, age, disability, protected veteran status, military or uniformed service member status, or any other status or characteristic protected by applicable laws, regulations, and ordinances. If you need assistance and/or a reasonable accommodation due to a disability during the application or the recruiting process, please send a request to [email protected].