Data Scientist

Summary

Guidehealth is a data-powered healthcare company focused on improving patient health, healthcare affordability, and provider outcomes through AI, predictive analytics, and value-based care. The Data Scientist will analyze clinical, claims, and healthcare data to support Clinical, Quality, and CDI performance goals, while developing production code, validating data and models, and communicating actionable findings to clinical and technical stakeholders.

Responsibilities

• Partner with Clinical, Quality, and CDI teams to understand operational goals and business objectives, and identify where data science can support them
• Perform statistical and machine learning analyses of clinical, claims, and other healthcare data, employing causal inference, predictive modeling, risk stratification, time-series analysis, and data visualization
• Apply clinical intelligence and relevant literature throughout the analytic process, validating that cohort definitions, code sets, and model features accurately reflect real-world clinical practice and documentation patterns
• Develop and maintain SQL and Python code for replicable analyses and production data pipelines
• Communicate analytic results to technical and non-technical stakeholders through clear visualizations, presentations, and written summaries
• Perform data QA and validation activities, including scripted and manual checks for data format, completeness, and accuracy

Skills

• Bachelor's degree in a quantitative or technical field such as Data Science, Statistics, Biostatistics, Epidemiology, Health Informatics, Computer Science, or equivalent experience
• 2+ years of experience applying data science, statistics, or advanced analytics to healthcare data (clinical, claims, or EHR) in a research, clinical, or business setting
• Working knowledge of clinical workflows and terminology, including familiarity with clinical vocabularies and coding systems (e.g., CPT, ICD-10-CM, SNOMED CT, RxNorm, LOINC, NPI)
• Understanding of healthcare operations such as care management, risk adjustment, quality improvement, revenue cycle, prior authorization, and value-based care
• Proficiency in SQL and Python for data querying, analysis, and pipeline development, with working knowledge of Bash for script execution
• Solid grounding in applied statistics, including hypothesis testing, regression, model evaluation, and causal inference concepts
• Experience with data integration and ETL work, including data normalization and processing, SFTP, and API connections
• Experience using Git-based source control (e.g., GitHub) throughout a software development lifecycle for production code
• Experience with data QA and validation processes
• Familiarity with at least one major cloud platform (AWS, GCP, or Azure)
• Strong communication and presentation skills for interfacing with both clinical and technical audiences
• Advanced degree (MS or PhD) in Biostatistics, Epidemiology, Health Informatics, Data Science, or a related field, or clinical licensure combined with formal data science training
• 2+ years of experience in a clinical care, clinical informatics, or CDI setting or degree, licensure, or certification in nursing, pharmacy, medicine, public health, or a related clinical field
• Experience with AWS services such as S3, Lambda, and Step Functions
• Familiarity with the Arcadia Analytics Foundry database
• Proficiency with cross-team project tracking and documentation tools such as Jira and Confluence

Qualifications

Must Haves

• Bachelor's degree in a quantitative or technical field such as Data Science, Statistics, Biostatistics, Epidemiology, Health Informatics, Computer Science, or equivalent experience
• 2+ years of experience applying data science, statistics, or advanced analytics to healthcare data (clinical, claims, or EHR) in a research, clinical, or business setting
• Working knowledge of clinical workflows and terminology, including familiarity with clinical vocabularies and coding systems (e.g., CPT, ICD-10-CM, SNOMED CT, RxNorm, LOINC, NPI)
• Understanding of healthcare operations such as care management, risk adjustment, quality improvement, revenue cycle, prior authorization, and value-based care
• Proficiency in SQL and Python for data querying, analysis, and pipeline development, with working knowledge of Bash for script execution
• Solid grounding in applied statistics, including hypothesis testing, regression, model evaluation, and causal inference concepts
• Experience with data integration and ETL work, including data normalization and processing, SFTP, and API connections
• Experience using Git-based source control (e.g., GitHub) throughout a software development lifecycle for production code
• Experience with data QA and validation processes
• Familiarity with at least one major cloud platform (AWS, GCP, or Azure)
• Strong communication and presentation skills for interfacing with both clinical and technical audiences

Nice to Haves

• Advanced degree (MS or PhD) in Biostatistics, Epidemiology, Health Informatics, Data Science, or a related field, or clinical licensure combined with formal data science training
• 2+ years of experience in a clinical care, clinical informatics, or CDI setting or degree, licensure, or certification in nursing, pharmacy, medicine, public health, or a related clinical field
• Experience with AWS services such as S3, Lambda, and Step Functions
• Familiarity with the Arcadia Analytics Foundry database
• Proficiency with cross-team project tracking and documentation tools such as Jira and Confluence

Benefits

• Work from Home: Guidehealth is a fully remote company, providing you the flexibility to spend less time commuting and more time focusing on your professional goals and personal needs.
• We offer comprehensive Medical, Dental, and Vision plans to keep you covered.
• Our 401(k) plan includes a 3% employer match to your 6% contribution.
• We provide Life and Disability insurance. Additionally, we offer voluntary Life options.
• Our Employee Assistance Program (EAP) is here to help you through tough times.
• We offer paid time off plans helping you achieve work-life balance and meet your personal goals.
• Guidehealth offers paid parental leave to give you the time you need.
• Guidehealth offers various resources dedicated to your learning and development to advance your career with us.
• All full-time employees of Guidehealth who work 30 hours per week or more are eligible for our comprehensive benefits package.
• Guidehealth provides new employees with the necessary equipment to function in their role at no charge to the employee.