Data Scientist

Overview

Cotiviti is seeking a Data Scientist to lead the development of advanced classification and predictive systems for healthcare risk adjustment and ICD-10 code classification. This role will focus on building intelligent NLP systems that analyze clinical charts and encounters to accurately identify and classify ICD-10 codes through sophisticated pattern recognition, machine learning, and natural language processing techniques. The position includes working on MLOps and MCP initiatives and will be a key contributor to the Edifecs Business Unit AI innovation project, driving cutting‑edge AI solutions across the healthcare technology portfolio.

• Lead development of NLP-based classification systems for ICD-10 code identification from clinical charts and encounters.
• Design and implement deep learning models using PyTorch and transformer architectures for medical text analysis.
• Design and implement Model Context Protocol (MCP) for LLM governance, including model registry, deployment orchestration, and performance tracking systems.
• Implement comprehensive MLOps frameworks including CI/CD pipelines for model deployment, A/B testing infrastructure, and production model monitoring.
• Build and optimize machine learning models for accurate risk adjustment coding and HCC classification.
• Develop decision support systems for automated ICD-10 code suggestion and validation.
• Create and maintain feature engineering pipelines for clinical text processing and model training.
• Implement model evaluation metrics and performance optimization strategies for healthcare coding accuracy.
• Produce comprehensive technical documentation and training materials for NLP models.
• Conduct system health checks and performance monitoring for deployed coding models.
• Collaborate with engineering teams to integrate ML/NLP solutions into production systems.
• Provide technical guidance on statistical modeling, transformer architectures, and algorithm selection.
• Support data pipeline design and implementation for clinical text analytical workflows.
• Participate in code reviews and maintain high standards for code quality.
• Experience with distributed computing frameworks and big data technologies for processing large volumes of clinical data.
• Mentor junior scientists and analysts in machine learning, NLP, and artificial intelligence best practices.
• Track record of using assistive AI technology to improve the quality and efficiency of modeling and analytics.
• Complete all responsibilities as outlined in the annual performance review and/or goal setting.
• Complete all special projects and other duties as assigned.
• Must be able to perform duties with or without reasonable accommodation.

• Bachelor's degree in Computer Science, Statistics, Mathematics, Data Science, or related field;
  Master's in Data Science or related field preferred.
• 3+ years of experience in machine learning and AI with a focus on NLP, classification, and predictive systems.
• Strong expertise in PyTorch and transformer architectures (BERT, RoBERTa, etc.) for text classification.
• Proficiency in Model Context Protocol design and implementation for enterprise LLM governance.
• Experience with MLOps tools and frameworks (MLflow, Kubeflow, Weights & Biases) and LLM deployment platforms.
• Advanced Python programming skills with experience in NLP frameworks and libraries.
• Experience with healthcare claims data, clinical text processing, and ICD-10 coding systems preferred.
• Knowledge of risk adjustment methodologies and HCC (Hierarchical Condition Categories) coding.
• Experience with feature engineering techniques for clinical text and model evaluation methodologies.
• Experience with model deployment and monitoring in production environments.
• Understanding of data quality frameworks and error detection methodologies for healthcare coding.
• Strong analytical and problem‑solving skills with a focus on clinical data challenges.
• Excellent communication skills with the ability to explain technical NLP concepts clearly.
• Experience with version control systems and collaborative development practices.
• Expertise with SQL and data manipulation tools for healthcare datasets.

Cognitive / Mental…