AI & Data Scientist (Remote)

📋 Description

• • Own end-to-end data science solutions by translating ambiguous healthcare and operational problems into AI/ML models that deliver measurable impact, from problem framing through model deployment and feedback loop implementation.
• • Build and deploy production-grade AI/NLP/LLM models for clinical document understanding, including OCR, named entity recognition (NER), embeddings, and vision models to support autonomous chart review and documentation analytics.
• • Advance Alignment Healthcare’s proprietary clinical intelligence platform, AVA, by developing next-generation models that enhance risk score accuracy and CMS audit preparedness (RADV) for Medicare Advantage operations.
• • Design and implement automated quality and payment integrity tools to reduce manual review, increase accuracy, and surface documentation anomalies and audit risks.
• • Partner with Product, Engineering, and Clinical leaders to embed data science into critical workflows including claims processing, utilization management, provider network optimization, and risk adjustment.
• • Develop clinical intelligence features such as disease detection, compliance forecasting, and quality analytics using high-volume, high-dimensional, and unstructured data.
• • Ensure engineering excellence by creating reusable internal libraries, maintaining coding standards, conducting code reviews, and writing clear technical documentation.
• • Manage the full lifecycle of deployed models, including monitoring for data drift, setting up alerting systems, and performing post-deployment reviews to ensure model performance and regulatory alignment.
• • Utilize Python and SQL to build scalable data pipelines, CLI tools, and reusable software packages with strong focus on data quality and modular design.
• • Leverage Databricks (Spark, Delta Lake), MLflow, Unity Catalog, Git, CI/CD, and Docker to support model development, experimentation tracking, and production deployment.
• • Integrate with REST/GraphQL APIs and orchestration systems to enable seamless data flow between clinical, claims, and analytics systems.
• • Communicate complex technical findings effectively to non-technical stakeholders through data visualization and storytelling, ensuring alignment across clinical, compliance, and engineering teams.
• • Collaborate cross-functionally in a fast-paced, ambiguous environment to prioritize initiatives that maximize clinical outcomes and regulatory compliance.
• • Champion best practices in machine learning experimentation, experimental design, and model validation to ensure robust, auditable, and scalable solutions.