Focused on developing AI-powered solutions using machine learning, data-driven approaches, and emerging AI technologies.

• Interested in Applied AI, Machine Learning, Computer Vision, and Natural Language Processing (NLP).
• Experienced in researching, evaluating, and experimenting with AI models and emerging technologies.
• Interested in Generative AI, AI integration, and Retrieval-Augmented Generation (RAG).
• Enjoy turning AI concepts into practical, real-world applications and integrating them with web technologies and software systems.
• Passionate about combining data-driven approaches and AI to solve real-world problems.
• Driven by continuous learning, research, experimentation, and hands-on development.

• AI & Data Science: Machine Learning, Deep Learning, Computer Vision, NLP, Generative AI, RAG
• Programming: Python, SQL, JavaScript, Java
• AI & Software Integration: AI APIs, REST APIs, FastAPI, Software Engineering
• Frameworks & Tools: PyTorch, TensorFlow, Scikit-learn, Pandas, NumPy, Hugging Face, Git
• Development: Android Development, ROS 2, Gazebo, Robot Navigation

An end-to-end AI-powered system for child malnutrition screening, developed in response to the challenges of malnutrition in Gaza. The project involved developing and evaluating multimodal AI models to analyze child images and extract anthropometric measurements and nutritional status classifications, then integrating the trained models into a web application to transform the research into a practical, user-oriented solution.

An intelligent AI agent designed to support clinicians in selecting appropriate medicines and dosages for diabetes care. The project combines a LangGraph-based reasoning agent with a Retrieval-Augmented Generation (RAG) pipeline, using ChromaDB for vector retrieval, PostgreSQL for structured data, and OpenRouter LLMs to provide grounded, context-aware recommendations based on retrieved medical reference data.

A data-driven project developed to analyze the prevalence of disease-related symptoms in Gaza through a structured community survey. The project involved designing and distributing the survey, cleaning and preprocessing the collected data, performing exploratory data analysis, and visualizing symptom patterns and related factors.

A comparative study of parametric and non-parametric classification methods on the Two Moons dataset. The project involved implementing MLE, MAP parameter estimation, EM, Parzen-window KDE, and KNN, followed by comparing their decision boundaries, accuracy, sensitivity to hyperparameters, and computational behavior.

Applied AI, Generative AI, RAG, multimodal systems, AI model deployment, intelligent software integration, and research-driven AI development.

Exploring AI research, experimental evaluation, and technical writing, with a focus on turning research ideas into practical AI solutions and academic work.

• LinkedIn: Zahra'a Alderawi

Feel free to reach out for collaboration, research discussions, project opportunities, or simply to connect and share ideas.