Zuha Beyabani
Software Engineer
Building innovative solutions across Frontend, Backend, and AI/ML
About Me
I'm a passionate software engineer with expertise spanning across multiple domains. I love building scalable applications, creating intuitive user experiences, and exploring the cutting edge of artificial intelligence and machine learning.
With a strong foundation in both frontend and backend development, I bring full-stack capabilities to every project. My experience in AI/ML allows me to integrate intelligent features and data-driven solutions into applications.
I'm always eager to learn new technologies and tackle challenging problems that make a real impact.
Skills & Expertise
Frontend
- React
- Next.js
- TypeScript
- JavaScript
- HTML/CSS
- Tailwind CSS
Backend
- Node.js
- Python
- REST APIs
- GraphQL
- Databases
- Microservices
AI/ML
- Machine Learning
- Deep Learning
- TensorFlow
- PyTorch
- NLP
- Computer Vision
Featured Projects
Basic LLM from Scratch
AI/MLBuilt a large language model from the ground up, implementing transformer architecture, attention mechanisms, and training pipeline. Demonstrates deep understanding of neural network fundamentals and NLP.
MNIST & Iris Dataset Analysis
Data ScienceComprehensive data analysis and machine learning exploration of classic datasets. Implemented various classification algorithms, feature engineering, and visualization techniques to extract insights.
ML for Space Debris Orbital Paths
AI/MLMachine learning model to predict and analyze orbital trajectories of space debris. Applied predictive modeling techniques to address space sustainability challenges.
Interactive Tic-Tac-Toe with AI
Full-StackWeb-based tic-tac-toe game featuring 5 AI opponents implementing different strategies: Random, Goal-Based, Utility-Based evaluation, Minimax, and Alpha-Beta Pruning. Explored game theory algorithms and optimal decision-making in adversarial games.
Surah Quiz
Web DevelopmentInteractive quiz game where users select a surah and are challenged to fill in the blank for missing words in each ayah. Tests knowledge of the Quran through an engaging, educational format.
ML Wiki RAG Pipeline
AI/MLEnd-to-end Retrieval-Augmented Generation system with multiple chunking strategies (fixed, sentence, semantic, recursive), hybrid dense + sparse retrieval with cross-encoder re-ranking, and comprehensive IR evaluation metrics.
ChessGPT
AI/MLGPT-style transformer trained to predict chess moves by learning from a grandmaster's games. Built a custom tokenizer for chess notation, implemented logit masking for legal move generation, and explored how language models can capture individual playing styles.
Play Tic-Tac-Toe
Your turn!
You are X, AI is O (Minimax Algorithm)
Powered by Minimax Algorithm
The AI uses optimal strategy - you can't beat it, but you can tie!