Data Scientist

Job Summary

Advanced proficiency in Python Hands-on experience in Docker and Kubernetes

Responsibilities

• Advanced proficiency in Python Hands-on experience in Docker and Kubernetes
• Analyze large scale Medicare and Medicaid claims and payer datasets using Python to uncover actionable patterns that improve care quality cost efficiency and operational performance across the organization.
• Develop validate and deploy predictive and classification models focused on claims utilization payment integrity fraud waste and abuse detection and member risk stratification to support data informed decisions.
• Design and implement end to end data pipelines from ingestion through feature engineering and model serving ensuring reproducible workflows and high quality data for downstream analytics and reporting.
• Collaborate with product actuarial clinical and operations teams in a hybrid work model to translate complex business questions into clear analytical problems and deliver measurable outcomes for stakeholders.
• Create interpretable model outputs and explainable analytical frameworks so that non technical partners can trust and use insights in policy design benefit configuration and claims processing decisions.
• Evaluate Medicare and Medicaid policy changes and payer business rules through data driven experimentation and scenario analysis providing evidence based recommendations that align with regulatory requirements.
• Optimize Python code queries and data structures for performance on large claims datasets ensuring solutions are scalable maintainable and compliant with internal standards and external obligations.
• Document methodologies assumptions and analytic decisions in clear narrative form to support auditability reuse of models and consistent knowledge sharing across distributed teams.
• Partner with data engineering teams to define data quality checks address source system issues and enhance claims and payer data assets for long term analytical value.
• Communicate findings through concise visual narratives and written summaries that connect statistical results to member outcomes financial impact and societal benefits in healthcare delivery.
• Contribute to continuous improvement of analytical practices by proposing new methods tools and reusable components that raise the overall maturity of data science in the organization.
• Support hybrid collaboration by participating in onsite and remote working sessions ensuring smooth coordination of model development testing and deployment activities during day shifts.
• Uphold ethical standards in data science by carefully handling sensitive health information and evaluating models for fairness and bias across member populations.

Qualifications

• Demonstrate advanced proficiency in Python for data manipulation statistical modeling and machine learning including experience with common data science libraries suitable for large scale claims analysis.
• Bring deep practical experience working with Medicare and Medicaid claims and payer data including familiarity with coding systems adjudication processes and policy driven business logic.
• Apply strong knowledge of data wrangling and feature engineering techniques to transform complex healthcare claims into reliable analytic datasets ready for modeling and reporting.
• Utilize sound understanding of statistics and machine learning to select appropriate methods validate model performance and ensure robust findings that stand up to regulatory and business scrutiny.
• Show capability to work effectively in a hybrid environment during day shifts coordinating with cross functional teams while maintaining focus on delivery timelines and quality standards.
• Exhibit clear written and verbal communication skills to present technical work to diverse audiences and document approaches for reuse and compliance.