The Opportunity at Komodo Health

This role is critical to designing and implementing data processing and analysis programming pipelines for Life Science/HEOR/RWE research studies utilizing the Komodo Healthcare Map.

Looking back on your first 12 months at Komodo Health, you will have…

• Develop programming pipeline to perform large-scale data extraction, transformation, and validations to facilitate high-quality HEOR/RWE studies using SQL
• Implement and execute analytic plans for observational research studies using Komodo data
• Perform complex statistical modeling in a programming language such as R/Python/SAS
• Take ownership of the analysis pipeline to generate results, and ensure that results align with study objectives and statistical approaches in the research protocol
• Present interim and final results internally for review by stakeholders, incorporate feedback to the analysis pipeline and iterate on analytic plans as needed.
• Create final deliverables in industry standard to share with external clients
• Design and implement standardized programs for reproducible research.

You will accomplish these outcomes through the following responsibilities…

• Collaborate with cross-functional teams to design and execute observational research studies.
• Write efficient, well-documented SQL queries to extract, transform, and analyze large volumes of healthcare data, implementing descriptive summary, statistical analysis, and data visualization for HEOR/RWE projects
• Validate analysis results, troubleshoot issues, and iterate on analytic approaches to ensure alignment with research protocols and study objectives
• Implement best practices in reproducible research, including version control, documentation, and standardized programming workflows, while contributing to publications, conference presentations, and internal knowledge sharing

What you bring to Komodo Health:

• Background/education in Statistics, Biostatistics, Data Science, Public Health, Epidemiology, or other relevant disciplines is preferred.
• At least three years of industry experience working with large-scale databases using SQL (data query, data cleaning, data transformation).
• Experience working with a large healthcare database (preferably administrative claims or EHR).
• Experience working in a research team collaborating with subject-matter experts on epidemiological research studies.
• Basic understanding of concepts used in epidemiological study design. 
• Experience performing statistical analysis (descriptive analytics, regression, hypothesis testing, and visualization).
• Proficient in implementing statistical methods in programming languages such as R/Python/SAS.
• Willingness to learn new tools and methods in order to deliver best-in-class results. 

Considered as a plus:

• Advanced SQL skills, familiar with frameworks such as dbt
• Familiar with standard programming practices such as version control and git.
• Extensive knowledge of epidemiological study design.
• Advanced knowledge in statistical modeling in the healthcare research area: PSM, KM, Cox model.
• Experience working with the healthcare system.
• Published manuscripts using claims data.
• Experience with other programming languages.

#LI-REMOTE