DATA & MACHINE LEARNING ENGINEER

From data.
To impact.

I engineer data and machine learning solutions to solve complex problems. My focus is on building scalable systems from raw data processing to model deployment.

Cairo, EgyptData EngineeringMachine LearningOpen to DE & ML roles
Donia Mostafa
ABOUT ME

I am Donia Mostafa, a Computer Engineering graduate from El Shorouk Academy with practical experience in Data Engineering, Machine Learning, and MLOps.

I manage the complete data lifecycle including data preparation, pipeline construction, model building, and system deployment.

My background includes ETL processes, data warehousing, recommendation systems, computer vision, and ML tracking through training programs at NTI, DEPI, Huawei, and ITI.

PythonSQLData PipelinesMachine LearningSparkMLflow
EXPERIENCE

Experience

2026 NTI

DataOps Engineering

ETL ELT, data pipelines, warehousing, Spark, PySpark, Hadoop, HDFS, Kafka, and scalable processing.

2025 to 2026 DEPI

AI & Data Science

End to end ML workflows, recommendation systems, evaluation, experiment tracking, and MLflow.

2024 ITI

AI & Machine Learning

ML and deep learning fundamentals, preprocessing, feature engineering, and model evaluation.

2024 HUAWEI

HCIA AI

AI ecosystem, deep learning, computer vision, NLP, GANs, Transformers, and deployment.

SELECTED WORK

Projects

Personalized Recommendation System
01 FLAGSHIP PROJECT 2026

Personalized Recommendation System

An end to end hybrid e commerce recommendation system that combines collaborative and content based approaches and improves through user feedback.

Turn user interactions into personalized product recommendations.
Hybrid recommendation with weighted rank fusion and a feedback loop.
Preprocessing, feedback weighting, model integration, evaluation, MLflow tracking.
Python ALS BPR TF IDF MLflow
18.5%Recall@10
10.7%NDCG@10
82.4%Coverage@10
AI based Air Defense System
02 GRADUATION PROJECT 2025

AI based Air Defense System

A graduation project applying computer vision and deep learning to real time aerial target detection, tracking, and localization.

Detect and track aerial targets in real time.
YOLO based detection pipeline integrated with tracking logic.
Dataset preparation, annotation validation, augmentation, splitting, detection and tracking.
YOLOv5n Computer Vision Python
Diabetes Dataset Analysis Grid
03 MACHINE LEARNING 2024

Diabetes Prediction System

A machine learning project exploring patient data through preprocessing, feature engineering, classification, regression, and clustering.

EDA, preprocessing, scaling, feature engineering, and tuning.
Regression, classification, and K Means clustering.
Accuracy, Precision, Recall, and F1 Score.
Elbow Method for selecting the clustering structure.
TOOLKIT

Technical skills

Data Engineering

  • Python
  • SQL
  • ETL ELT
  • Data Pipelines
  • Data Warehousing
  • PySpark
  • Apache Spark

Machine Learning

  • Scikit learn
  • TensorFlow
  • PyTorch
  • Regression
  • Classification
  • Clustering
  • Hyperparameter Tuning

AI Systems

  • YOLO
  • Object Detection
  • Image Processing
  • Tracking Systems
  • ALS
  • BPR
  • TF IDF

MLOps & Tools

  • MLflow
  • Git
  • GitHub
  • Docker
  • Streamlit
  • Pandas
  • NumPy
RECOGNITION

Recognition

AWARD 2025

Outstanding Performance Award

ITC EGYPT awarded for the AI based Air Defense System project.

ACHIEVEMENT 2025

Certificate of Achievement

IEEE Egypt IC SIT 2025 International Competition.

Outstanding Performance Award
Certificate of Achievement
PROFESSIONAL PROOF

Explore my work

GET IN TOUCH

Let's turn data
into impact.