Passionate AI & Data Science student with expertise in machine learning, deep learning, and full-stack development. Currently pursuing B.Tech in Artificial Intelligence and Data Science at Amrita Vishwa Vidyapeetham. I specialize in building intelligent systems, from LLM-powered applications to computer vision solutions.
Amrita Vishwa Vidyapeetham
Aug 2023 – Aug 2027
DIGITAL WOM PRIVATE LTD
Mar 2025 – May 2025 (Remote)
Built a B2B lead generation system with interest-based targeting and developed a full-stack multi-agent platform featuring social media integration (LinkedIn/Instagram), content brainstorming, OCR processing, and Neo4j knowledge graph visualization. Created comprehensive AI agent ecosystem with knowledge graph integration for enhanced lead generation and content creation workflows.
Trioma Health Private Limited (Traze AI)
June 2025 – Nov 2025 (Remote)
Built a Gemini LLM-powered medical coding system to automatically classify ICD-10, CPT, and HCPCS codes from patient case files,Achieved 92.2% overall accuracy and 98.3% organ-level precision across 2,027 test cases (MedCodex/MedMNIST) using ensemble validation.
Feb 2025
Advanced microbiome causality analysis system for Stanford University combining Granger causality tests to identify causal relationships. Built AI validation pipeline with web scraping and custom deep research workflow to confirm microbiome cause-effect pairs.
Private RepoDec 2024
Built an AI-powered Streamlit application that converts domain-specific research papers into structured datasets using NER pipelines. Leverages Spacy Toolkit and Groq API powered model evaluation to ensure high-quality entity extraction.
Source CodeMar 2024
A Generative Visual Question Answering model designed to understand images and generate natural language answers. Combines computer vision and NLP to process visual inputs and text-based queries accurately.
Source CodeMay 2025
Advanced RAG system combining chain-of-thought reasoning (RARE) with intelligent multi-strategy retrieval capabilities for document-based QA. Features dynamic knowledge base routing and ChromaDB vector storage.
Source CodeMay 2025
Universal integration framework bridging MCP tools, A2A agents, and LangChain components into unified AI workflows. Features automatic agent discovery and dynamic protocol conversion.
Source CodeThis paper presents the design and implementation of a self-controlled delivery robot designed for autonomous navigation and secure last-mile delivery. The system utilizes GPS-based positioning along with an A* path planning algorithm to determine an optimal path to the target location. Computer vision methods alongside a forward-facing HD camera provide lane keeping and real-time obstacle detection by employing a YOLOv8 model. Hazards on the road initiate a local bypass procedure to realign its trajectory dynamically. During delivery, the system requests a one-time password (OTP) from the receiver, which will activate an onboard lock mechanism for the release of the parcel.
View on IEEE XploreDeepLearning.AI (Coursera)
Amrita University Coimbatore