CoverageAI◦ Spearheaded the development of a comprehensive AI Agent designed to answer all coverage related user queries for an insurance policy. Leveraged PDF policy documents and contracts and generated responses with citations and references.◦ Engineered an algorithm capable of parsing PDF documents into graph structures, facilitating robust context building for Retrieval Augmented Generation (RAG) models.◦ Built a Knowledge Graph from unstructured text using LLM and utilized it to traverse and retrieve context related to user queries.LLM / Generative AI based solution for Enterprise Data◦ Created LLM agent using LangChain to answer adjuster queries based on a large pool of pdf/rtf/text documents (unstructured data) containing multiple text sections and tables.◦ Developed LLM chain to chat with multi-table database (structured data)to fetch required information using queries and respond using a combination of text and tables wherever required.Claims Triaging◦ Developed ML solutions to effectively triage claims across various divisions, resulting in a 35% improvement in claims processing time while maintaining 95% accuracy.

Productivity Scoring and Optimization◦ Created ML models to evaluate adjuster productivity based on processing time, and revenue generated considering the individual workload, types and size of claims handled.◦ Build forecast model for incoming claims and estimate adjuster capacity requirements, resulting in a 25% reduction in claim backlog and a 20% reduction in average claims processing time through effective resource allocation.Claims Processing Timeline Analysis◦ Developed a real-time claim tracking dashboard to monitor operations KPIs like claims processed, average processing time, and milestone achievement trends.Text-to-SQL Semantic Parsing◦ Developed a deep learning algorithm for a Text-to-SQL engine for complex and cross-domain semantic parsing of natural language queries on relational databases◦ Built a natural query suggestion model to assist users in query formation for the databaseScanned Legal Document Processing◦ Automated the process of data and entity extraction using OCR, ICR, Computer-Vision and NER◦ Performed data mining and visualized crucial information◦ Built dashboards, reports and machine learning models to visualize and bring out deeper insights from the data

Face Recognition based Attendance system◦ Developed a deep learning-based face recognition and attendance system and deployed it in multiple educational institutions with a real-time accuracy of over 99% running on low-end edge device.

AutoNav Ground Robot with Interactive Modules◦ Designed and built a miniature ground robot based on Raspberry-Pi for autonomous surveillance using off-board processing◦ Implemented SLAM algorithm for stereo camera based 3D point cloud mapping and navigation of robot◦ Integrated face and voice recognition modules in the robot to interact with users and navigate on verbal commands