Engineered automated PDF table extraction pipeline using custom regex patterns, Python, and NLP techniques, processing 500+ documents and improving data parsing accuracy by 20% for manufacturing workflows. Built intelligent keyword detection system with targeted pattern matching algorithms, reducing manual verification by 35% and accelerating document processing speed by 3x. Collaborated with cross-functional teams of 15+ members to integrate automation tools with existing quality management systems, delivering customer-facing features ahead of schedule. Optimized data extraction workflow with Pandas and NumPy, enabling seamless integration with production databases and reducing data entry errors by 45%.

Research Intern at Vivekanand Education Society’s Institute of Technology

May 1, 2025 - July 1, 2025

Curated and preprocessed domain-specific dataset of 5000+ labeled samples using Python, OpenCV, and data augmentation techniques, enhancing model training reliability and achieving 91% augmentation rate. Implemented and benchmarked 3 state-of-the-art architectures (CNN+LSTM, I3D, YOLOv8+ResNet) using TensorFlow and PyTorch, optimizing for accuracy, precision, recall, and F1-score across 10 performance metrics. Achieved 93.87% accuracy, 0.9376 F1-score, and 94.2% precision with YOLOv8+ResNet hybrid model, outperforming baseline models by 12% and demonstrating production-ready performance for real-time deployment. Optimized model inference pipeline through quantization and pruning techniques, reducing prediction latency by 40% (from 150ms to 90ms) while maintaining high accuracy for real-time applications. Conducted comprehensive model evaluation with confusion matrices, ROC curves, and cross-validation, generating detailed technical documentation for research publication.

Software Development Intern at Essel Fabricators PVT. LTD

November 1, 2024 - December 1, 2024

Architected and deployed a production-ready full-stack web application using TypeScript, Next.js, and React, managing 500+ quality inspection records with real-time monitoring capabilities. Engineered OCR-based document digitization to automate handwritten quality control notes (10+ documents weekly). Developed advanced search, filter, and export features with optimized SQL queries and database indexing, achieving instant data retrieval (2s response time) and a 25% performance improvement. Implemented RESTful API backend services with Node.js and PostgreSQL, ensuring 99.9% uptime through robust error handling and caching mechanisms.

Software Development Intern at Essel Fabricators Pvt. Ltd.

November 1, 2024 - December 1, 2024

Designed and deployed production-ready full-stack web application using TypeScript, Next.js, and React to manage 500+ quality inspection records with real-time monitoring, improving inventory tracking. Implemented OCR-based document digitization using Google Cloud Vision API to automate handwritten quality-control notes (10+ documents weekly). Built advanced search, filtering, and export features with optimized SQL queries and indexing, delivering instant data retrieval and a 25% performance boost. Created RESTful API backend services with Node.js and PostgreSQL, handling 10+ daily API requests with reliable error handling and caching mechanisms.

Research Intern at Vivekananda Education Society's Institute of Technology

May 1, 2025 - July 1, 2025

Curated and preprocessed domain-specific dataset of 5000+ labeled samples using Python, OpenCV, and data augmentation techniques, enhancing model training reliability and achieving 91% augmentation rate. Implemented and benchmarked 3 state-of-the-art deep learning architectures (CNN+LSTM, I3D, YOLOv8+ResNet) using TensorFlow and PyTorch, optimizing for accuracy, precision, recall, and F1-score across 10 performance metrics. Achieved 93.87% accuracy, 0.9376 F1-score, and 94.2% precision with YOLOv8+ResNet hybrid model, outperforming baseline models by 12% and demonstrating production-ready performance for real-time deployment. Optimized model inference through quantization and pruning techniques, reducing prediction latency by 40% (from 150ms to 90ms) while maintaining high accuracy for real-time applications. Conducted comprehensive model evaluation with confusion matrices, ROC curves, and cross-validation, generating detailed technical documentation for research publication.