Ahmed Alaa

I am an aspiring Artificial Intelligence engineer with a strong passion for building intelligent systems that solve real-world problems. I enjoy working on projects involving Machine Learning, Deep Learning, Computer Vision, and Data Analysis.

My current toolkit includes Python, TensorFlow, OpenCV. I'm particularly interested in deploying models that work reliably in real-world conditions — not just in notebooks.

When I'm not training models, I'm exploring the latest research in computer vision and looking for open-source projects to contribute to.

1. Nov 2025 — Present

   Internship - Machine Learning Specialist · Digital Egypt Pioneers (DEPI)

   In this training, I trained on how to create models related to Machine Learning,, Deep Learning, Computer Vision, NLP, and others

   • Python
   • Matplotlib
   • Seaborn
   • Numpy
   • Pandas
   • TensorFlow
   • Keras
   • OpenCV
   • Mediapipe
   • Scikit-learn
2. Aug 2025 — Oct 2025

   Internship - Machine Learning · National Telecommunication Institute (NTI)

   I was trained on how to build classic machine learning models, then we moved on to the Deep Learning part, and the Transfer Learning.

   • Python
   • TensorFlow
   • OpenCV
   • Scikit-learn
   • Pandas
   • Numpy
3. Apr 2024 — Dec 2024

   Internship - Data Analyst Specialist · Digital Egypt Pioneers (DEPI)

   Completed a practical training program focused on data cleaning, analysis, and visualization using tools like Python, SQL, and Power BI.

   • Python
   • SQL
   • Power BI
   • Tableau
   • Excel
   • Matplotlib
   • Seaborn
4. Jul 2023 — Sep 2023

   Internship - Python Training · Thebes Academy

   I learned the Python language, and the course focused on it, in addition to some important libraries in the language.

   • Python
   • Pandas
   • Numpy
   • Matplotlib

• EmoVision - AI Engagement Detection

  A graduation project tackling automatic engagement detection from video. The system ingests an uploaded video, extracts spatial and temporal features using computer vision, and classifies engagement state via a trained XGBoost model.

  • Python
  • OpenCV
  • FastAPI
  • NumPy
  • Pandas
  • Python
  • MediaPipe
  • Scikit Learn

  
• Liverpool Players Attendance

  A computer vision system that automatically tracks Liverpool FC player attendance by detecting and recognizing faces from Anfield arrival footage.

  • Face Recognition
  • OpenCV
  • dlib
  • NumPy
  • Pandas
  • Python

  
• Real Time Drowsiness Detection

  A real-time computer vision system that detects driver drowsiness by analyzing eye behavior using facial landmarks and deep learning.

  • TensorFlow
  • Keras
  • MediaPipe
  • OpenCV
  • Scikit Learn
  • Python

  
• Food 101 Classification

  A deep learning image classification model trained on the Food-101 dataset to identify 101 food categories. Achieved high accuracy using transfer learning with fine-tuned convolutional neural networks.

  • TensorFlow
  • Keras
  • OpenCV
  • Scikit Learn
  • Pandas
  • Python

  
• Sign Language Detection

  A project on Sign Language Detection for only three gestures: (Hello, Thanks, I love you). It used several techniques such as LSTM and others. The results showed an 88% accuracy rate in testing.

  • TensorFlow
  • Keras
  • OpenCV
  • Scikit Learn
  • Pandas
  • Python
  • Mediapipe