Healthcare AI Data Scientist

We are seeking a Fractional AI Data Scientist with deep healthcare analytics experience to support the design of agentic AI workflows, build LLM-powered tools, and structure data pipelines from EHRs, payer systems, and clinical sources. Your work will power intelligent automations for Eligibility Verification, Pre-Authorization, Risk Stratification, and more.

You’ll work closely with solution architects, automation engineers, and clinical SMEs to ensure healthcare data is structured, insightful, and responsibly applied in AI contexts.

📌 Key Responsibilities

Build and fine-tune AI/ML/NLP models tailored to healthcare datasets (structured & unstructured).

Design intelligent prompts and evaluation pipelines using LLMs (OpenAI, Azure OpenAI).

Work with healthcare data from Epic, Cerner, Availity, and claims sources to build actionable insights.

Partner with Azure engineers or Workato specialists to build data-driven agentic workflows.

Cleanse and transform healthcare data (FHIR, HL7, CSV, SQL) for modeling and automation triggers.

Ensure all solutions comply with HIPAA and ethical AI best practices.

Visualize outcomes for business and clinical teams, and document models for reuse.

🧠 Required Skills & Experience

5+ years in data science with at least 2+ in healthcare-specific roles.

Experience with clinical data (EHR, EMR, payer claims) and healthcare ontologies (ICD-10, CPT, FHIR).

Hands-on with LLM tools (OpenAI, LangChain, RAG frameworks) for classification, summarization, or chatbot use cases.

Strong proficiency in Python, SQL, Pandas, and ML/NLP frameworks.

Familiarity with PHI/PII handling and compliance frameworks like HIPAA.

⭐ Preferred Qualifications

Azure AI stack (OpenAI, Data Factory, Synapse)

Experience in conversational AI, intake automation, or clinical note summarization

Worked in or with a digital health, healthtech, or AI startup environment

Understanding of automation platforms (Workato, Power Automate)

🛠️ Tech Stack

Languages: Python, SQL, PySpark

AI/ML: Scikit-learn, OpenAI, Hugging Face, LangChain, Transformers

Data: Azure Data Factory, Snowflake, BigQuery, Postgres

Integration: FHIR APIs, REST APIs, Postman

Visualization: Power BI, Streamlit, Tableau

Compliance: HIPAA, De-ID, RBAC