
AI assistant for Educational YouTube videos
Turning YouTube Learning into an Interactive Experience

Welcome

I believe great software isn't just built—it's imagined, designed, and refined. With a passion for AI and product thinking, I engineer meaningful digital experiences that learn, adapt, and perform.
Building an ML-driven UN SDG classifier website leveraging sentence transformers to analyze repositories and issues, providing actionable insights on how open-source projects align with UN Sustainable Development Goals.
Developed and deployed a full end-to-end computer vision system for grocery item recognition and labeling, encompassing model benchmarking (YOLOv7, Faster R-CNN, SSD) and selection for production, modular ML pipeline design with efficient retraining, OCR integration for packaging text, large-scale dataset annotation and segmentation with Mask R-CNN, and optimization for mobile edge deployment (via ONNX and TensorRT), collectively improving accuracy, speed, and reliability of real-time product identification.
Engineered and led the full lifecycle of a secure, performance-optimized Enterprise Reporting Dashboard—integrating React.js/Next.js, AWS Lambda, and Django-based access control—to streamline data access for 20+ department heads, enforce role-based compliance for sensitive academic records, and deliver responsive, user-driven features through iterative stakeholder collaboration.
Spearheaded the design and delivery of scalable full-stack solutions across healthcare, sustainability, and logistics domains—building modular CMS platforms, real-time analytics dashboards, and cross-platform communication systems—leveraging modern stacks (React.js, Node.js, Flask, Electron.js) and agile CI/CD practices to cut development turnaround by 60%, boost reporting accuracy by 20%, and streamline operational decision-making for diverse clients.
Designed a Hybrid data collection application that enabled 50+ volunteers to gather over 1,000 speech samples, contributing to a 30% performance boost in CNN model accuracy through PyTorch-driven deep learning optimizations.

A Machine Learning Approach to Prosthetic Hand Control
This project focuses on using electromyography (EMG) signals from the human arm, processed through deep learning and neural networks, to control the movements of a prosthetic hand. By training an artificial neural network on EMG signal datasets, the system learns to accurately interpret muscle patterns and translate them into real-time prosthetic actions, offering a potential solution for people without hands.

Using A* Algorithm for Efficient Navigation
The project aims to develop hardware and software-based solutions for indoor path planning and tracking of a mobile robot, using the A* shortest path finding algorithm in MATLAB. The focus is on accurate calibration of the path to ensure successful displacement and navigation between any two positions on a predefined indoor map.

Using LIDAR for Enhanced Object Detection
The project focuses on utilizing LIDAR technology to improve blind spot detection in autonomous vehicles. By integrating LIDAR sensors with advanced machine learning algorithms, the system aims to accurately identify and classify objects in the vehicle's blind spots, enhancing overall safety and navigation capabilities.
Featured Projects

Explore the intersection of decentralized AI technologies and international governance frameworks. Understand the challenges and opportunities in this evolving landscape.

Explore the intersection of AI technologies and hardware development. Understand the challenges and opportunities in this evolving landscape.

Delve into the complexities of humor and sarcasm in AI interactions. Can AI truly understand and generate humor?

Explore the challenges of building trustworthy AI agents in gaming. How can we ensure fairness, accountability, and transparency?

Explore the challenges of deploying AI models in healthcare settings. What are the potential risks and ethical considerations?
Let's Chat! Whether you have a question, a project idea, or just want to connect, I'm always happy to hear from you. Drop me a message, and I'll be in touch soon!