Journey

A timeline of the milestones that shaped how I think and what I build, from classrooms and competitions to research and code.

Where I've Worked
Nov 2025 — Jun 2026

Researcher & Data Scientist | Preboot.ai

At Preboot.ai, I worked on data analytics, probabilistic modeling, and validating AI agent features. On the data side, I focused on marketing analytics, using tools like PyMC-Marketing and XGBoost to study customer conversion paths and forecast long-term user behavior. I also spent time evaluating LLM performance, validating synthetic research methods against human reliability metrics, and analyzing memory architectures for AI systems.

Aug 2024 — Oct 2024

Mobile Development Intern | CivilSoft

During the internship, I developed two distinct mobile applications using React Native. The first was a core business application focused on seamless data synchronization, where I built and integrated secure RESTful API pipelines. The second was an interactive AI assistant app, where I implemented a contextual chat interface powered by fine-tuned Hugging Face models to support different user personas.

Honors & Awards
Jul 2024

NU Quantum-AI Hackathon — 3rd Place Winner

Developed a QML classification model using Qiskit Machine Learning.

Mar 2020

International Mathematical Olympiad — 2nd Filtration

Qualified through Ideasgym.

Oct — Dec 2019

International Youth Math Challenge — Bronze & Special Honor

Special Honor for submitting the solution as a digitally written document.

Mar 2019

Kangaroo Mathematics Competition — Diploma of Excellence & Gold Honor

Provided by Edumeter Egypt.

Research
IEEE · Dec 2025

Empowering Silent Voices: Adaptive EEG-to-Text Systems for Assistive Technologies

Abstract: Translating brain activity into natural language represents a transformative frontier in human-machine interaction and assistive communication technology for individuals with speech impairments. While electroencephalography (EEG) has shown promise for neural decoding, existing EEG-to-text methods remain constrained by closed vocabularies, limited semantic expressiveness, and inadequate accommodation of intersubject neural variability. This work presents a novel framework that transcends traditional closed-vocabulary limitations by synergistically combining subject-adaptive representation learning with advanced natural language processing architectures. Our approach employs deep neural networks to extract discriminative EEG features, enabling the generation of complex sentences that extend beyond the constraints of training data. Experimental evaluation on the ZuCo corpus demonstrates substantial improvements across multiple metrics, including BLEU, ROUGE, and BERTScore, surpassing state-of-the-art baselines. The framework effectively produces semantically coherent and grammatically accurate text while adapting to individual neural signal patterns through personalized modeling. By bridging open-vocabulary text generation with neural signal interpretation, this research establishes foundations for practical brain-to-text communication systems. The interdisciplinary implications span assistive technology innovation and personalized communication interfaces, advancing the paradigm of brain-computer interaction across clinical, research, and consumer applications.

IEEE · Dec 2023

Improving Diabetes Forecasting: An Ensemble Approach with Feature Selection in Time Series Analysis

Abstract: Addressing the global health challenge of diabetes through the lens of time series analysis, our study leverages machine learning to advance prediction and management. Introducing various models-linear regression, random forest, gradient boosting, elastic net regression, and support vector regression-implemented in Python with a dataset from GitHub, our methodology emphasizes meticulous data preprocessing and feature selection. Among the explored ensemble techniques, the combination of linear regression, random forest, and gradient boosting stands out, achieving a low mean squared error of 16.17. This underscores the potential of our approach to enhance diabetes prediction accuracy and improve management within time series analysis.

Skills

Each skill opens up; a live look at the projects, research, and work where I actually put it to use.

Bayesian Inference & Statistical Modelling
Analyzed PyMC Labs research including PyMC-Marketing at Preboot.ai to construct Bayesian Media Mix Models, focusing on Adstock and Hill transformations for accurate marketing attribution and long-term Customer Lifetime Value forecasting.
Generative AI & Local LLM Pipelines
Developed a zero-cost local implementation of PyMC Labs' Semantic Similarity Rating (SSR) algorithm using Ollama (llama3.2 & nomic-embed-text), optimizing pipeline latency with VRAM keep-alive constraints and structural fail-overs for restricted data sizes. Built InsightMiner, a custom RAG system for localized Markdown querying.
Python & Automation
The backbone of my engineering workflow. Used across local mathematical modeling pipelines, an asynchronous ASCII evaluation dashboard, a custom Rubik's Cube 3D solver with webcam detection, and productivity tools like FileFlow and Kindle Highlights Organizer.
Mobile Development (React Native)
Architected and deployed two distinct mobile applications during my CivilSoft internship, handling secure RESTful API synchronization and integrating fine-tuned Hugging Face AI chat assistants.
Research & Technical Writing
Experienced in translating complex deep learning methodologies and statistical papers into clear, structured syntheses. Formally typeset complex document layouts in LaTeX, resulting in two published peer-reviewed IEEE papers alongside independent technical methodology logs.
Knowledge Sharing & Collaboration
Proven track record of contributing to open-source concepts, building accessible tools for the developer community (like Equation Bridge for Google Docs), and collaborating within fast-paced startup teams at Preboot.ai.