Software Engineer, AI and data science student

Mohamed Amine Fakhre-Eddine

Software Engineer, and AI & data science student with a keen interest in Cybersecurity, and Robotics, as well as a detailed knowledge of AI concepts and architectures, and multiple collaborations in the software engineering world.

Technical skills

Programming languages C, Python, Java, PHP, JavaScript, TypeScript
Machine learning / Deep learning / Data science Pytorch, Keras, Hugging Face, Transformers, Numpy, Pandas, Scipy, Scikit-learn, Matplotlib
Databases MySQL, PostgreSQL, Oracle Database + SQL Developer, SQLite, MongoDB
Web backend AdonisJS, Flask
Web frontend Svelte (Sveltekit), Astro, Tailwind, HTML/CSS
Mobile Native android development
BI / Data analysis Power BI, KNIME
Project management Linear, MS project
Other tools Git, VS Code, Neovim, Docker, Linux, OpenCV, NLTK
Communication Arabic (Native proficiency), English (Professional working proficiency), French (Professional working proficiency), German (Limited working proficiency)

Experiences

AI/ML enginering intern

July 2024 - September 2024

3D SMART FACTORY — Remote — Mohammedia, Morocco

  • • Team of 1
  • • Built a chatbot for scientific research papers analysis
  • • Python, Hugging Face, PyTorch, Kaggle, Google Colab, Langchain/Langserve, SvelteKit, ChromaDB, MongoDB, Docker

Machine leaning intern

April 2023 - June 2023

Faculty of science and technology — Settat, Morocco

  • • Collaboration with Mechanical Engineering, team of 2 students
  • • Visualized and analyzed data, developed RNN-based machine learning model to detect faults in rotating machinery.
  • • Python and libraries like Matplotlib, Numpy, Pandas, Scipy, Keras, Scikit-learn.

Projects

Faculty chatbot - Academic project

A chatbot for the Faculty of Sciences and Techniques of Tangier (FSTT) using a combination of retrieval-augmented generation (RAG) and fine-tuning techniques. The chatbot is designed to provide accurate and contextually relevant responses to a wide range of queries related to the academic environment at FSTT. The RAG technique is used to extract information from PDF files and generate responses based on the context derived from these embeddings. The fine-tuning process involves adapting pre-trained language models (Llama 3 8B instruct) to understand and generate text specific to the academic context of FSTT. The chatbot is integrated into a user-friendly interface that allows users to choose between the RAG and fine-tuned models based on their preferences or needs. It was developed using a wide range of tools and technologies, including Hugging Face, PyTorch, Kaggle, Google Colab, Unsloth, Langchain/Langserve, SvelteKit, ChromaDB, MongoDB, and Docker. The architecture of the chatbot consists of three Docker containers: the User Interface (UI) container, the API container, and the Model container. The chatbot is deployed using a MongoDB database to store app-specific data, such as conversations and history. Tech stack: Python, Hugging Face, PyTorch, Kaggle, Google Colab, Unsloth, Langchain/Langserve, SvelteKit, ChromaDB, MongoDB, Docker

Twitter sentiment analysis app - Academic project

Twitter Sentiment Analysis system that leverages a Kafka and Spark pipeline to ingest and analyze Twitter posts in real-time, providing instant sentiment predictions using a pre-trained logistic regression model with cross validation. The user-friendly web interface, developed with Svelte, allows users to initiate and view sentiment analysis jobs. A Flask-based RESTful API facilitates communication between the interface, the processing system, and a MongoDB database that stores prediction results. The entire system is containerized using Docker for seamless deployment and orchestration with Docker Compose, ensuring high portability and manageability. Tech stack: Python, Kafka, Spark, Svelte, Flask, MongoDB, Docker

Content-Based Image Retrieval system based on Bayesian Relevance Feedback

A Content-Based Image Retrieval (CBIR) system that enables efficient image search and management through visual features and relevance feedback mechanisms. Users can upload, download, delete, and categorize images into predefined classes, as well as generate new images by applying transformations like cropping and scaling. The system computes and displays visual descriptors for images, including color histograms, dominant colors, Gabor texture filters, Hu moments, and additional custom descriptors. It supports both basic search to retrieve visually similar images and an advanced Bayesian relevance feedback mechanism to iteratively refine results, providing an intuitive and dynamic way to explore the RSSCN7 dataset, which consists of 2,800 images categorized into seven scene types such as Residential, Forest, and Industry. Tech stack: Python, Flask, OpenCV, NumPy, Pandas, Scikit-learn, Angular

Content-Based 3D Models Retrieval system

A web application designed to implement a robust Content-Based 3D Models Retrieval system that enables efficient image search and management through visual features. Users can upload, download, delete, and categorize models into predefined classes. The system computes and displays shape descriptors for models, including Zernike moments, and Fourier descriptors, in addition to viewing the model in 3D. It supports a simple search to retrieve visually similar models, providing an intuitive and dynamic way to explore the Pottery dataset. Tech stack: Python, Flask, NumPy, Pandas, Scikit-learn, Three.js, Angular

Article: Smart Poultry Farming with Edge AI for Real-Time Monitoring

Developed a theoretical framework integrating Edge AI and IoT technologies to monitor and manage poultry farming in real-time. The system uses sensors, edge computing devices, and cloud services to optimize environmental conditions and ensure poultry health. Key features include GRU and CNN models for predicting gas concentrations and assessing animal weight and health, aiming to enhance efficiency, reduce costs, and support sustainable poultry farming practices.

Eghata

Eghata is a transformative project designed to unite volunteers and individuals in need of assistance across Morocco. Building upon the existing Nt3awnou نتعاونو platform, Eghata focuses on aiding those impacted by crises, including the recent Moroccan earthquake and Libya floods. Our mission is to create an efficient hub for connecting volunteers with people seeking help throughout the country or the world. It was done with the leadership of my brother STORMIX, and the art direction of my brother MAADLOU. I was part of the first brainstorming and idea gathering, then contributed to the development of our UI, and API endpoints. This project I’m proud of the most because it reflects my commitment to leveraging technology for social impact and community support, and it was dedicated for our country. Tech stack: Typescript, React, AdonisJS, CapacitorJS, Redis, PostgreSQL, Tailwindcss

End-of-studies project - Academic project

In the Industry 4.0 context, this project focuses on using Python programming to extract temporal features from vibrational signals of rotating machinery. These features aid in fault detection without causing harm. The process encompasses data collection, feature extraction, and AI-based fault identification, enhancing predictive maintenance. Tech stack: Python, Keras, Pandas, NumPy, SciPy, sklearn, Matplotlib

Data playground desktop - Academic project

Data playground is an academic project that facilitates access to the world of machine learning for non-computer scientists, empowering users to seamlessly upload, process, visualize, and save their data. The app offers comprehensive data manipulation features, including handling missing values, duplicates, outliers, and feature selection. It also enables users to explore their data through various plots, in addition, the user can easily partition for training and testing sets. At end, the app empowers users to train, test, and save machine learning models, providing a comprehensive solution for data exploration and analysis. Tech stack: Python, CustomTkinter, Tkinter, Pandas, NumPy, SciPy, sklearn, Matplotlib

Mobile contacts app - Academic project

Android contacts app using Java and Android Studio. This app facilitates adding, updating, and deleting contacts, while also enabling seamless calling and messaging. Streamlining communication and organization for users on the go. Tech stack: Java, Android Studio

E-commerce website - Academic project

During my university's Web Development module, we created an E-commerce website as a learning project. We focused on user-friendly design and functionality, integrating features like product management, shopping cart. Tech stack: HTML, CSS, JavaScript, PHP

Interests

My wife, Gaming.

Contact

Feel free to reach out on [email protected], I would love to hear from you, whether you have an interesting project in mind, a suggestion for a cooperation, or you just want to get in touch. Together we can bring your concepts to life. Your suggestions and comments are really helpful to me. eager to get in touch!