Skip to content
View shilpamusale's full-sized avatar

Highlights

  • Pro

Block or report shilpamusale

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
shilpamusale/README.md

Shilpa Musale

AI/ML Engineer | Generative AI, LLMs, RAG & Agentic AI | MLOps | HealthTech

Software engineer with a decade in software engineering and HealthTech, now specializing in Generative AI and production-ready MLOps. With deep healthcare domain experience and two peer-reviewed publications, my focus is building scalable, reliable AI systems that solve real-world problems. I thrive on moving complex models from prototype to deployment, with an emphasis on mitigating hallucination, model interpretability, and test-driven development.


Featured Publications


Pinned Projects

Project Description Key Technologies
vertex-care Operationalized my peer-reviewed research on patient readmission by building an agentic MLOps platform that generates actionable intervention plans for high-risk patients. Google Gemini, ReAct Agent, LLM Feature Extraction, FastAPI, GCP Cloud Run, CI/CD
scholar-agent An advanced multi-agent research assistant using LangGraph, a Knowledge Graph (Neo4j), and a re-ranking RAG pipeline to reason over scientific papers. LangGraph, Google Gemini, Neo4j, ChromaDB, sentence-transformers
claim-triage-ai An intelligent healthcare claim triage pipeline that predicts denials, clusters root causes via NLP, and routes high-priority claims for automated processing. XGBoost, Sentence-BERT, Clustering, FastAPI, Streamlit, Docker, CI/CD
Cross-Site Otoscopy Domain Adaptation A deep-learning study on unsupervised domain adaptation for cross-site medical imaging — adapting a ResNet50 classifier across institutional datasets (DANN/MCC/CORAL) with occlusion-based interpretability analysis. (co-first author; manuscript in preparation) PyTorch, ResNet50, Domain Adaptation, Interpretability

Skills & Tools

Python PyTorch scikit-learn TensorFlow LangChain LangGraph Vertex AI FastAPI Docker GitHub Actions MLflow Neo4j


Pinned Loading

  1. scholar-agent scholar-agent Public

    An advanced multi-agent research assistant using LangGraph, a Knowledge Graph (Neo4j), and a re-ranking RAG pipeline to reason over scientific papers.

    Python 1

  2. vertex-care vertex-care Public

    Operationalized my peer-reviewed, published research on patient readmission by building an agentic MLOps platform to generate actionable intervention plans.

    Python

  3. claim-triage-ai claim-triage-ai Public

    An end-to-end ML system to automate Revenue Cycle Management (RCM) by predicting claim denials, analyzing root causes, and optimizing resolution workflows.

    Python

  4. medcode-agent medcode-agent Public

    Python