• Engineered large-scale web scraper using Scrapy and Playwright to extract AI research data from 13,900+ URLs, achieving 97% time reduction (15 min to 27 sec/article) with 90% relevancy
• Developed rate-limited crawler system with robots.txt validation for 139 universities, automating multi-format data extraction (Markdown, JSON, CSV) for 100+ URLs per institution
• Implemented automated logging and validation pipeline with error tracking mechanisms, processing 10,000+ academic articles into structured datasets for NLP/GenAI analysis

• Engineered batch testing framework to evaluate RAG architectures, analyzing 100+ test cases across LangChain and LlamaIndex implementations, resulting in 45% improvement in response accuracy and framework optimization
• Developed streamlined data pipeline processing 2000+ library resource pages with 6-category classification system, handling 200+ monthly queries to enhance chatbot knowledge base and response relevancy
• Designed and implemented responsive Streamlit interface with suggestion chips and feedback systems, integrating insights from UX workshops to optimize data collection and user interaction patterns

• Engineered real-time IoT analytics dashboard with ECharts visualizations for 100+ devices, implementing 7-second refresh rates and unified interface to reduce operator decision time by 40%
• Developed asset tracking system integrating Google Maps API for 500+ combines across 3 international airports, achieving 90% location accuracy with custom movement interpolation
• Optimized Angular application through code splitting and infinite scroll pagination, reducing load times by 50% (10s to 5s) for data-intensive interfaces

MS, Computer Engineering, Data Science Specialization

Expected December 2025

BTech, Electronics and Communications Engineering

July 2017 - July 2021