I am a technology enthusiast who has developed software in eHealth, business, education, and cybersecurity. I focus on backend engineering, developing AI tools and data microservices. I hold an MSc in Computing and IT Management from Cardiff University and a Bachelor's in Computer Engineering from HBKU. I also studied Electrical Engineering at Texas A&M and Computer Science at Carnegie Mellon. I am proficient in programming languages including Python, C, Java, MATLAB, Verilog, VHDL, and 8051 Assembly.
Project Mjölnir: An AutoML Pipeline for Brute Force Combinatorics Analysis
Developed an innovative automated brute-force pipeline for training and evaluating dataset-model combinations in binary image classification, with wildfire detection as a use case. The pipeline enables systematic testing of pre-trained models like ResNet50 and MobileNet across diverse datasets, reducing training time by up to 93.94% while improving performance metrics by 6.67%. It features user-configurable flexibility, integration of advanced evaluation metrics, and compatibility with modern frameworks like TensorFlow-Keras. This project showcases expertise in machine learning automation, and computer vision, with potential applications in various classification tasks.
Project HARPY: Safeguarding Networks from Malicious IoT Devices
Developed an innovative system to detect and classify rogue IoT devices in network environments using advanced machine-learning techniques. The solution integrates tools like Joy and Sleuth Kit to preprocess network traffic and a Random Forest-based classifier trained on large-scale datasets for accurate device categorization. Deployed on a Raspberry Pi with real-time updates delivered via Firebase-powered mobile apps, the system demonstrated high accuracy across multiple time scales. Designed with modularity, scalability, and user-centric functionality, this project underscores expertise in IoT security, machine learning, and full-stack development with potential applications in enterprise, residential, and governmental contexts.
Project Zamanya: Empowering Doctors to Analyze Patient Sleep Patterns
Zamanya is an eHealth ML package that uses incoming sleep data to identify and analyze good and bad sleep segments using an in-house trained model. It involves various visualizations for clustering and segmentation of data against an existing dataset, empowering doctors to derive useful information on the case at hand.
I completed this work during the summer going through an internship program with Qatar Computing Research Institute (QCRI). I worked mostly on the backend developing the preprocessing part of the package, including code that fetches raw sleep data via the Fitbit API and data mappers that output CSVs in the format usable by the package. This would help in training the model using the new data.
This work constitutes my earliest step into data preprocessing and feature extraction for AI applications.
Because I’m bound by NDA, I am not allowed to share my work and it remains as a property of QCRI. References are available upon request.
Shopify Integration Gateway: Automating Order Fulfillments and Tracking
A Flask-based RESTful API that allows Shopify merchants to interface with a Fleet Management System directly. Allowing for Shopify order fulfillments to be sent to the system through HMAC-secured webhooks. Granular fulfilment progress updates are then sent back to the merchant through the gateway through another set of webhooks.
This project showcases my ability to develop robust solutions to real-life business problems in the Fleet Management and Order Fulfillment Industry (Uber, Deliveroo, JET, etc.), enabling merchants to more easily facilitate order fulfilment and tracking processes using a single integration.
Cryptocurrency Investment Adviser (CIA): Informing Crypto Investment Decisions
This program is meant to be used as a helper for investors when making decisions related to cryptocurrency investments. It uses current trends to advise on whether to invest or withdraw cryptocurrencies into fiat currency. The measurement uses the instantaneous gradient as well as best line fit of the past 24 hours of data. Analysis was done using a modified version of the Ordinary Least Square (OLS) regression method.
This was my first big Python project, and I developed it because it was relevant to my work in the trading field at the time. And it coincided with the crypto bubble!
Computer Science Outreach: Upskilling People
For a full year, I have worked as a Development and Delivery Officer at Cardiff University’s School of Computer Science to develop and deliver various computer science materials and workshops to aspiring engineers of different ages and backgrounds. I, along with three of my colleagues, were collectively nominated for the national STEM Team of the Year 2024 for our contribution to computer science education across the country.
Some of the highlight workshops I have developed include a novel Flutter cross-platform app development mentorship series, a Machine Learning Intro workshop, a cybersecurity course for high school students, and several Python and JS workshops for web app development targeted at mature professionals and undergraduate students. The Flutter workshop I developed has become the team’s flagship workshop, being showcased in the BIG Event 2024 as the department’s workshop of choice.
Python-based Social Media Web App Development: Flask-based Dynamic Website
A Flask-based website that uses various web technologies including MySQL for data storage, OpenShift for deployment, Jinja for templating HTML pages, and Bootstrap 5 for styling.
This work showcases my web app development skills for something as complicated as a functioning social media platform, taking into account special requirements such as media handling, account security, privacy, and post/comment management and other user engagement features.
Web Scraping and Scripting: Passport Visa Requirements Scraper
A Python program that uses MechanicalSoup (an extension of BeautifulSoup) to scrape passport visa requirements data from The Passport Index to output a CSV file containing each country's passport visa requirements for all the countries abroad.
This program was developed during my internship at sKora Tech, and demonstrates an ability in automating data acquisition tasks to help in achieving internal business objectives.
Source code bound by NDA.
Computer Hardware: Project PH03N1X Prebuild (Timelapse Video)
Preparing a Threadripper-based system for a live building session. Got many more videos and documentation available upon request.
This was a passion project that shows my interest in all things tech, beyond professional software development endeavours.
An Interesting Challenge: Wordle-solving Bot
A Python-based program that uses a dictionary of known words and the feedback of a word’s Wordle configuration (yellows/grays/greens) to give the best matching word for the current configuration.
This was a fairly challenging little piece of work made during my time learning Python.
Proxy Server Setup (Presentation Video)
In this video, I explain the basic functions of a proxy server. FreeProxy was used to make a simple implementation for live demonstration.
