I am a passionate Computer Science engineering student, currently pursuing a dual degree in Artificial Intelligence and Data Science. I have strong experience in mobile development, backend, machine learning, and deep learning, with a keen interest in innovation and solving complex problems through advanced technologies.
Methodology: Agile (Scrum)
Tasks:
• Developed an automated pipeline using Generative Adversarial Networks (GANs)
to generate synthetic images of cells (viruses, bacteria, microbiomes).
• Optimized and trained deep learning models for microbiology.
• Created integrated applications based on scientific research techniques.
• Coupled these services with microservices.
• Integrated models into the cloud for scalable deployment.
Methodology: Agile (Scrum)
Tasks:
• Developed a Point of Sale application (attendance tracking, ticketing, cafés, restaurants).
• Built a Flutter frontend interface for an intuitive user experience.
• Contributed to several backend tasks using Spring Boot (database management and service integration).
• Implemented a simple yet efficient solution to collect, store, and exchange digital loyalty tokens.
Methodology: Agile (Scrum)
Tasks:
• Developed an e-commerce mobile application for Android with an intuitive Java interface
and backend features via Firebase (data management, authentication).
• Designed an optimized user experience, including navigation by category and
a personalized shopping cart.
Companion for a person with reduced mobility (Ry©Om).
Engineering Program in Artificial Intelligence & Data Science
Software Engineering Degree
Preparatory Cycle in Computer Science
Flutter, Swift, SwiftUI, Java, Kotlin
Python, PyTorch, TensorFlow, Keras, NumPy, Pandas, scikit-learn, NLTK, spaCy
Node.js, Spring Boot, .NET, SQL, MongoDB, Firebase
Scrum, GitHub, GitLab, Jira
A mobile application for personalized meal planning, offering recommendations
tailored to user goals such as weight loss or muscle gain. Integrates a machine
learning model to provide precise and engaging diet plans.
Tasks:
• Developed the cross-platform mobile app in Flutter (modern UI).
• Created a Node.js backend (authentication, RESTful API logic).
• Deployed and integrated a machine learning model with Flask (Python).
• Used MongoDB to manage user profiles and food data.
• Deployed on Microsoft Teams to ensure recommendation accuracy and optimize performance.
SoulLift is a mobile application focusing on mental well-being, offering a
personalized chatbot, motivational quotes, and time management tools. Includes
voice and emotional recognition for an optimized user experience.
Tasks:
• Collaboratively developed a cross-platform mobile app with Flutter, focused on mental wellness.
• Created a robust Node.js backend for real-time data (MongoDB).
• Integrated voice and emotional recognition features using a Python AI model,
combined with the ChatGPT API for mental health recommendations.
• Used GitHub for code version control and team collaboration.
An innovative disaster prevention app specialized in detecting earthquakes and
tsunamis through real-time server monitoring. Instantly alerts users and
proposes safe evacuation routes.
Tasks:
• iOS development: Built the application with SwiftUI for a modern and fluid UI.
• Android development: Developed the Android application in Kotlin.
• Web dashboard: Created an admin dashboard in Flutter for efficient management.
• Scalable backend: Implemented a robust Node.js architecture.
TreyDi is a bartering application designed to facilitate the exchange of items/products,
video games, cryptocurrencies, and even rare digital assets such as in-game objects (NFTs).
Tasks:
• Set up a complete exchange system (item ↔ item / service ↔ item / service ↔ service).
• Web development with Symfony 5.4 and Twig (MVC architecture).
• Desktop application in Java/JavaFX for deeper exchange management.
• Mobile application with Codename One.
• Agile Scrum methodology (project management, Jira).
Developed a deep learning model with YOLOv5 to detect and classify
various blood cells (white blood cells, red blood cells, platelets)
from medical images. Trained on a labeled dataset, optimized via
Google Colab, and validated with high accuracy. Covers data preprocessing,
model training, evaluation, and real-time inference for medical use cases.
Technologies: Python, PyTorch, YOLOv5, OpenCV, Google Colab
A task management application built with SwiftUI and Firebase, enabling users to create, view, and organize task lists intuitively.