Charvi Sharma | AI/ML Developer

iHub Dristi, TIH, Indian Institute of Technology, Jodhpur, India

• Developed a data-driven haptic simulation tool using iMSTK, Chai3D, and Random Forest for force feedback estimation in medical training.
• Integrated LangChain and LLMs to dynamically generate clinical scenarios for simulation environments.
• Designed and deployed a RAG pipeline with OpenAI embeddings and Chroma to ground LLM responses in medical data.

Icertis Solutions Pvt. Ltd., Pune, India

• Integrated apps like SFDC, Adobe, DocuSign, Citrix, Okta, etc., with the Icertis application and performed UI Customization on over 150+ customer instances.
• Built and maintained data pipelines for structured data ingestion and transformation, supporting ML-driven insights and contract generation.
• Designed and deployed automation tools and prompt-based GenAI modules using Python, .NET, and OpenAI APIs to streamline contract workflows across 150+ clients.

Icertis Solutions Pvt. Ltd., Pune, India

• Led migration and upgrade of large customer application pods (MT to MT), implementing API changes to newer versions, enhancing performance and reducing downtime by 50%.
• Worked on Microsoft Azure Resources and built an automated API to generate Azure APKs, integrating with the ICI platform. Built Azure-integrated APIs and AI-enhanced CLM workflows.
• Worked on the fine-tuning and optimization of ML models used in metadata extraction, clause tagging, and document summarization.

Indian Institute of Technology, Jodhpur, India

Poornima College of Engineering, Jaipur, India

LangChain, Prompt Engineering, Azure AI Studio, Python

Created LLM-driven dynamic scenarios for medical simulations using LangChain, Python, and semantic search. Built Python-based feedback loops, force prediction models, and vector pipelines for real-time scenario interaction. Integrated Azure AI Studio for seamless model deployment.

PyTorch, MMEngine, MMCV, Python

Developed AI Detect, leveraging PyTorch as its deep learning framework, supported by Python, MMEngine, and MMCV from the OpenMMLab ecosystem. Developed training, evaluation, and model integration pipelines entirely in Python to support 2D and 3D keypoint detection. Implemented custom data loaders, augmentations, and export tools for seamless model deployment and testing.