Statistician/ Data Scientist

Role overview

Responsibilities

• check_circle Analyze large healthcare, clinical, and operational datasets to identify trends, risks, and actionable insights.
• check_circle Apply statistical methods including regression, hypothesis testing, multivariate analysis, time series analysis, and forecasting.
• check_circle Formulate and solve modeling problems using numerical optimization techniques such as gradient-based methods, constrained optimization, and regularization.
• check_circle Evaluate optimization trade-offs including convergence, stability, and computational efficiency in model training and inference.
• check_circle Design, train, and evaluate predictive and machine learning models using Python, PyTorch, and supporting frameworks.
• check_circle Develop AI-driven systems to support clinical risk identification, patient triage, and care prioritization.
• check_circle Perform feature engineering, dimensionality reduction, and model selection using PCA, ICA, RFE, clustering, and ensemble methods.
• check_circle Build forecasting models for patient volume, no-show risk, and treatment outcomes.
• check_circle Implement data pipelines and analytical workflows using Python, SQL, and cloud-native tools on Linux environments.
• check_circle Package and deploy analytical and machine learning models using Docker for reproducibility and scalability.
• check_circle Support CI/CD workflows for data science and machine learning pipelines, including automated testing, model versioning, and controlled deployment.
• check_circle Deploy, monitor, and maintain models on AWS using services such as SageMaker, EC2, S3, and related infrastructure.
• check_circle Develop and operate analytical systems on Linux operating systems, including Ubuntu, for local development and production environments.
• check_circle Optimize performance-critical components using Rust or Rust-based libraries when appropriate for production systems.
• check_circle Document analytical methods, optimization assumptions, validation results, and model limitations for technical and non-technical stakeholders.
• check_circle Collaborate with clinicians, engineers, and researchers to integrate data science solutions into operational healthcare systems.

Basic qualifications

• Master’s degree in Statistics, Applied Mathematics, Data Science or a closely related quantitative field.
• Strong foundation in probability, statistical inference, and numerical optimization.
• Proficiency in Python and R for statistical analysis and machine learning.
• Experience with machine learning frameworks such as PyTorch and scikit-learn.
• Understanding of optimization methods used in machine learning, including loss functions, regularization, and iterative solvers.
• Experience building data pipelines and analytical workflows in Linux environments.
• Familiarity with Linux operating systems, including Ubuntu, for development and deployment.
• Familiarity with Docker and containerized deployment of data science systems.
• Exposure to CI/CD practices for analytics or machine learning pipelines.
• Experience using AWS for data storage, model training, deployment, and monitoring.
• Working knowledge of Rust or experience using Rust-based tools for performance optimization preferred.
• Strong communication skills with the ability to explain complex analytical and optimization concepts clearly.
• Must be a U.S. citizen or authorized to work in the United States on a permanent basis without current or future sponsorship.
• Master's (Required)
• Data science: 3 years (Required)
• Python: 3 years (Required)
• Rust (programming language): 1 year (Required)
• SQL: 2 years (Required)
• AWS: 1 year (Preferred)
• R: 2 years (Preferred)
• Kansas City, MO 64151 (Required)
• Confidential (Required)
• Day Shift (Required)
• Kansas City, MO 64151 (Required)
• Kansas City, MO 64151: Relocate before starting work (Required)
• 75% (Required)