Job description

Key Responsibilities - Data Engineering - Design, implement, and optimize OCR and data extraction pipelines for ingesting PDF referral forms and other healthcare documents. - Develop data transformation and mapping processes to store extracted data into an Azure SQL schema. - Build and maintain the medallion data architecture (Bronze/Silver/Gold) in Azure Data Lake Storage to support both application workflows and future analytics/model training. - Implement and optimize search indexing (Azure AI Search) for both structured and unstructured data. - AI/ML Development - Integrate Azure OpenAI or equivalent LLM services with retrieval-augmented generation (RAG) to support a natural language query feature. - Implement initial predictive analytics models (fall risk, infection risk, medication cost forecasting) using heuristics or light ML models, with a path to more advanced modeling in Phase 2. - Develop a compliance AI agent (MVP version) that runs scheduled checks on documentation and flags potential violations. - Collaborate with the Solution Architect to ensure AI components are secure, HIPAA-compliant, and cost-optimized. - Collaboration & Delivery - Work in Azure DevOps with sprint-based development, pairing with backend/API developers on AI integration points. - Participate in architecture/design reviews and provide input on data model decisions. - Document pipelines, AI integrations, and data flows for future handoff to the client’s internal team. - Support UAT for AI/data features, including tuning models and validating extracted data. Required Skills & Experience - Technical Expertise - Proven experience with Azure Data Services (Azure SQL, Data Lake Storage, Azure AI Search, Azure Functions). - Hands-on experience with OCR (Azure Form Recognizer / Azure Document Intelligence) and unstructured data processing. - Strong Python skills for AI pipeline and data processing development. - Experience integrating LLMs (Azure OpenAI) with RAG patterns. - Knowledge of basic predictive modeling techniques (classification, regression) and healthcare data compliance considerations. - Proficiency with REST APIs for integrating external systems (e.g., pharmacy, insurance). - Healthcare & Compliance - Understanding of HIPAA compliance and secure handling of PHI. - Familiarity with healthcare data formats and workflows (HL7, FHIR, eMAR). - Collaboration & Delivery - Prior experience working in agile, cross-functional product teams. - Ability to deliver end-to-end—from data ingestion to model integration to API exposure. - Strong documentation and knowledge transfer skills. Preferred Qualifications - Experience in healthcare software development (EHR, EMR, or related domains). - Familiarity with vector search and semantic search concepts. - Experience with Azure Machine Learning for model deployment. - Background in predictive analytics for healthcare outcomes.

Requirements