Data Scientist III, Causal Inference

About the position

We are looking for a talented Data Scientist III with a strong foundation in programming (R/Spark/SQL/Python) and extensive experience with claims data analysis to join our mission of improving patient care quality in communities nationwide. In this role, you will collaborate with our skilled team of statisticians, economists, and data scientists on our Causal Inference team, which is dedicated to rigorously evaluating the impact of our products and programs through advanced analysis of medical claims data. Your role will encompass a wide range of data processing and healthcare data analysis responsibilities, with a primary focus on developing, managing and optimizing the team’s data pipeline and codebase. This pipeline is crucial for generating modeling-ready datasets, performing statistical modeling, and producing quarterly business reports – all while ensuring efficiency, reproducibility and scalability. In your role you will also conduct exploratory data analysis, contribute to advanced causal inference modeling under the guidance of our team’s experts, and execute high-impact business analytics.

Responsibilities

• Process and Analyze Healthcare Data: Work with various types of healthcare data, including longitudinal claims data, to help teams quantify the relationships between healthcare quality and patient outcomes, such as cost, clinical outcomes, and care patterns.
• Maintain and Optimize Data Pipelines: Develop, run, and enhance data science and data engineering pipelines that create modeling datasets; run statistical models; and produce quarterly business reports.
• Improve and Troubleshoot Codebase: Review and optimize the team’s data ETL and statistical code, both legacy and in development, to enhance runtime and memory efficiency, ensure reproducibility, and support automation and scalability. Troubleshoot technical issues as they arise, working with the engineering team as needed for support.
• Conduct Ad-Hoc Analyses: Conduct ad-hoc analyses (e.g. of claims data) as business needs arise in a fast-paced environment to uncover business and clinical insights and support Covera Health’s strategy and decision-making.
• Advanced Statistical Modeling: Conduct advanced statistical modeling of claims data under the supervision of the team’s experts, utilizing methods like Generalized Linear Models, Matching for Causal Inference, and Difference-in-Differences. Apply statistical models and methods developed by the data science team to quantify program savings and ROI.
• Prepare and Communicate Insights: Assist in preparing documentation and presentation materials for client meetings and key deliverables, and effectively communicate analytical results to both internal and external stakeholders.
• Collaborate: Work closely with data science team members and other colleagues across Covera on data analysis requests, projects, and research initiatives.

Requirements

• M.S. or B.S. in Computer Science, Statistics, Biostatistics, Economics, Data Science, Applied Mathematics, or a related field.
• At least 2 years of experience for M.S. degree holders, or 5 years for B.S. degree holders.
• Strong foundation in data engineering and coding best practices, with expertise in R, Spark (specifically sparklyr), SQL, and Python for data science. Exceptional skills in R and sparklyr are required.
• Experience developing scalable code for use by a wider team and contributing to a collaborative codebase.
• Proven ability to troubleshoot code, technical issues, and data pipelines effectively.
• Strong understanding of, and experience working with, real-world medical and claims data, including familiarity with ICD codes, CPT codes, CMS-HCC models, and comorbidity coding.
• Experience with fundamental data science models, including Generalized Linear Models (GLM), Mixed Models and longitudinal data analysis.
• Proven ability and enthusiasm for working in a collaborative team environment, paired with a proactive, go-getter attitude.
• Willingness to learn new techniques and tackle diverse data science challenges at the intersection of healthcare and analytics.

Nice-to-haves

• Experience with (or enthusiasm to learn) causal inference methodologies, such as propensity score matching and difference-in-differences.
• Preferred experience working with payor organizations, healthcare consulting, and/or fast-paced, client-facing environments.

Benefits

• Competitive salary
• Stock options
• Medical, dental, and vision insurance
• HRA
• 401k
• Pre-tax commuter benefits
• Flexible paid time off
• Comfortable office space filled with various quality snacks and beverages