Lead Data Scientist, Causal Inference, Clinical Outcomes
1 day ago
New York
Job Description: Study Design & Execution: Lead a longitudinal, quasi-experimental study starting May 7 to measure clinical outcomes, specifically hospitalization frequency and discharge follow-ups. Causal Inference Modeling: Apply advanced methodologies (e.g., propensity score matching) to observational data to estimate counterfactual patient outcomes with minimal bias. Actuarial-Grade Validation: Develop and refine statistical models that will be thoroughly vetted and approved by customer actuaries. Stakeholder Management: Serve as the primary analytical face to SCMG, gathering requirements and aligning on clinical/business definitions of success. Data Storytelling: Translate complex statistical findings into compelling presentations and client-ready reports for both technical and non-technical leadership. Vendor Audit & Wrap-up: Extract usable value from an existing outsourced study, close out the vendor contract, and integrate relevant findings into the final study. Technical Infrastructure: Navigate and build analytics reporting infrastructure using SQL, Python, dbt, Redshift, and Looker. Project Handoff: Ensure all code is clean and reproducible for final handover to the internal Phamily BI team. Requirements: Health-Tech Expertise: Deep experience in causal inference, metric design, and clinical outcomes evaluation. Data Proficiency: Extensive experience working with complex EHR and healthcare claims data. Advanced Analytics Toolkit: Highly capable in Python, R, SQL, dbt, Redshift, and Looker. Statistical Matching: Proven experience developing algorithms for high-dimensional statistical matching with large datasets. Security Standards: Practical experience maintaining strict PHI security protocols while building data infrastructure. Analytical Rigor: Ability to design and execute actuarial-grade studies that control for significant confounding variables. Communication: Exceptional ability to synthesize technical data into narratives for non-technical clients. Education: Advanced degree in a quantitative field (e.g., Data Science, Statistics, Health Economics, or Epidemiology). Benefits: Competitive compensation commensurate with experience Potential to earn equity based on performance Medical, dental, and vision coverage for employees and dependents at a nominal cost Paid maternity leave FSA and Dependent Care account options 401(k) Eligibility after 6 months of full-time employment Collaborative, mission-driven work environment