I am an applied software engineer with a Master's in Computer Engineering, working on applied machine learning, natural language processing (NLP), and LLM-based systems. I currently design and deploy AI-driven document intelligence solutions at Deepixel FZ-LLC, focusing on building reliable systems that move beyond prototypes into real-world use.
My background combines academic research with hands-on software delivery. Alongside my graduate research, I have over three years of experience working with international clients, developing Python-based automation, data processing pipelines, and applied ML solutions.
My research interests include applied NLP, retrieval-augmented generation (RAG), and the optimization and evaluation of LLM-based document intelligence systems. I'm also interested in remote sensing and computer vision for high-impact, real-world applications.
Ghulam Ishaq Khan Institute
Sukkur IBA University
Research comparing the effectiveness of YOLO and Faster RCNN models for classifying cotton crops and weeds in agricultural environments, contributing to precision agriculture practices.
View on IEEE XploreA comprehensive analysis of various algorithms' performance characteristics when working with different types of sorted and unsorted data structures.
View on IEEE XploreMS thesis — estimated crop yield using Sentinel-2 multispectral satellite data with machine learning regression models, integrating NDVI and other spectral indices.
Comparative study of YOLO and Faster RCNN for detecting and classifying cotton crops vs. weeds in field images. Published at ICIT 2024.
Final year project — IoT-based crop monitoring using Raspberry Pi with environmental sensors for real-time data collection, logging, and remote alerts.
Licensed professional engineer with the national engineering regulatory body.