© Mapbox, © OpenStreetMap

Speaker

Rajeshwari Sah

Rajeshwari Sah

Rajeshwari Sah, Machine Learning Engineer at Apple

Sunnyvale, California, United States

Actions

I am a Machine Learning Engineer with specialized expertise in fine-tuning and aligning Large Language Models (LLMs), including proprietary models like CLINICALGPT, as well as LLAMA, ALPACA, and MISTRAL.

Currently a Machine Learning Engineer at Apple, I previously held a Lead Applied Scientist role at Fresh Gravity and Lifio.ai, where I focused on building AI agents, document extractors, and protocol document generators for complex, high-stakes domains.

My technical stack is geared toward production-scale AI, spanning Python, PyTorch, Golang, TensorFlow, and LangChain, with deep experience in vector databases like Pinecone, ChromaDB, Qdrant, and FAISS. I hold a Master of Science in Computer Science from UC San Diego, where I also served as a Graduate Teaching Assistant for algorithms and machine learning. I am passionate about translating cutting-edge AI research into robust, business-driving solutions.

Area of Expertise

  • Health & Medical
  • Information & Communications Technology
  • Real Estate & Architecture

Topics

  • Artificial Inteligence
  • Machine Learning and Artificial Intelligence
  • Artificial Intelligence (AI) and Machine Learning
  • Developing Artificial Intelligence Technologies
  • Artificial Intelligence
  • Artificial intellince
  • Machine Learning/Artificial Intelligence
  • Artifical Intelligence
  • The Future of Artificial Intelligence: Trends and Transformations
  • Artificial Intelligence & Machine Learning
  • Artificial Intelligence & Machine Teaching
  • RAG
  • GraphRAG
  • Data Science & AI
  • Data Science
  • python
  • AI Localization
  • Agentic AI
  • Agentic rags
  • Agentic Workflow
  • Agentic automation
  • Agentic Fraemworks
  • Agentic AI / Autonomous Agents
  • Multi-AI Agent
  • AI Agents & Multi-Agent Systems
  • AI Agent Systems
  • Machine learning and Artifical Intelligence
  • ai chatbots
  • AI assistants

Building an Agentic AI Medical Scribe with LangGraph: From Voice to Structured SOAP Notes

Medical documentation continues to be one of the biggest productivity bottlenecks in healthcare. In this hands-on workshop, participants will learn how to design and deploy an agentic AI medical scribe that transforms real or simulated doctor–patient conversations into structured SOAP (Subjective, Objective, Assessment, Plan) notes.
Using LangGraph, we’ll build a dynamic, multi-agent system where each node performs a specialized task and communicates through a shared memory graph:
Transcription Agent — converts clinical dialogue into text using a speech-to-text model.
Information Extraction Agent — identifies key clinical entities such as symptoms, vitals, and diagnoses.
Summarization Agent — generates structured SOAP notes and validates internal consistency through a self-reflective loop.

Attendees will see how LangGraph enables state-aware orchestration and real-time coordination between these agents, how to integrate retrieval grounding using clinical ontologies (ICD-10, SNOMED), and how to measure performance with F1, ROUGE-L, and readability metrics.
By the end, participants will deploy a lightweight, production-ready prototype that demonstrates how agentic workflows can automate time-consuming documentation tasks, while remaining transparent, auditable, and compliant.

Rajeshwari Sah

Rajeshwari Sah, Machine Learning Engineer at Apple

Sunnyvale, California, United States

Actions

Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.

Jump to top