Kawtar -

During my final year internship, I developed a Retrieval-Augmented Generation (RAG) system using GPT-4o to audit Git repositories for code clarity and standards compliance. I filtered and embedded relevant files, applied cosine similarity for selection, and used prompt engineering to extract structured JSON evaluations. I benchmarked GPT-4o across different repositories, analyzed score variability, and validated results against linters like Checkstyle and Pylint. The entire system was containerized with Docker and automated using a Makefile.

Developing a health indicator for Predictive Maintenance, with a focus on identifying and predicting failures in wind turbines, incorporating status codes and SCADA data. Implemented time series analysis using Python and utilized Long Short-Term Memory (LSTM) networks for binary classification. → Recognition: Results Presented at WindEurope’s 2024 Technology Workshop

Artificial Intelligence Club. • Participating in artificial intelligence competitions and programming competitions (Data challenge AI-PAU, etc...).

Company Discovery Internship at SANLAM ASSURANCE. • Ranking and management of automobile insurance claims. • Handling customer files in the health service department