Skip to content
View Nabil-Haddad's full-sized avatar
0 followers · 1 following

Achievements

Achievement: Pull SharkAchievement: Pair Extraordinaire

Achievements

Achievement: Pull SharkAchievement: Pair Extraordinaire

Block or report Nabil-Haddad

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Nabil-Haddad/README.md

Hi, I'm Nabil

MSc Artificial Intelligence · University of Kent
Building trustworthy AI systems that work in the real world.

What I'm Working On

My MSc dissertation focuses on Trustworthy Multimodal RAG for Medical Decision-Making — a system that combines retrieval-augmented generation with multimodal inputs (text + imaging) to support clinicians, with explainability and safety at its core.

Core research themes:

  • Trustworthiness: uncertainty quantification, hallucination mitigation, source attribution
  • Multimodality: fusing clinical text with medical imaging in a RAG pipeline
  • Medical AI: responsible deployment, regulatory-aware design

Tech Stack

Languages

Python Java C JavaScript

AI / ML

PyTorch TensorFlow HuggingFace scikit-learn OpenCV LangChain

Data & Visualisation

NumPy Pandas Matplotlib

Web & Backend

React Express FastAPI SQLAlchemy PostgreSQL MongoDB Docker

Auth & API Security

JWT bcrypt REST API

Focus Areas

Retrieval-Augmented Generation (RAG)
AI for Healthcare & Clinical Support
Responsible & Explainable AI
Async Backend Systems (FastAPI + SQLAlchemy 2.0)
Secure API Design (JWT Authentication, Password Hashing)

Open to research collaborations and AI/ML roles.

Pinned Loading

  1. OpinionMiner OpinionMiner Public

    End-to-end ABSA system: model fine-tuning, evaluation pipeline, FastAPI backend, and React dashboard — built research-first with five progressive notebooks

    Jupyter Notebook

  2. mini-rag mini-rag Public

    Minimal Retrieval-Augmented Generation pipeline in plain Python. ChromaDB + sentence-transformers + GPT-4o, no framework abstractions.

    Python

  3. NumPy-Mastery NumPy-Mastery Public

    Pure NumPy mastery, annotated notebooks, 40+ exercises with solutions, and an image processing pipeline built without OpenCV or scipy.

    Jupyter Notebook

  4. gridguard gridguard Public

    ML platform for detecting energy theft in smart grids — from raw meter data to a production-ready prediction API with a full operations dashboard.

  5. jwt-auth-contacts-api jwt-auth-contacts-api Public

    Secure RESTful contacts API built with Node.js, Express 5 & MongoDB, features JWT authentication, bcrypt password hashing, and strict per-user data isolation.

    JavaScript

  6. churn-lens churn-lens Public

    Leakage-aware churn prediction pipeline where the simplest model won, Logistic Regression (0.845 AUC) beat Random Forest by generalizing cleanly. EDA → preprocessing → model selection → SHAP explai…

    Jupyter Notebook