Mabrouk User

Designed a reconstruction-error based anomaly detection system for microservice systems. Developed an LLM-based OCR pipeline to convert financial documents to structured data and incorporated new research into TTS pipelines.

Conducted systematic experiments on dozens of architectures for Arabic dialect TTS and ASR. Implemented 3+ production ready generative TTS architectures using PyTorch and Transformers, and designed quantitative and qualitative testing pipelines for generative model evaluation.

Programmed a custom HR chatbot with 95% query resolution rate using REST and WebSocket APIs. Streamlined collaboration through Discord, GitHub, and Trello, reducing manual status updates by 75%, and deployed production bot and SQLite database on Raspberry Pi.

Authored a CNN-XGBoost hybrid model for COVID-19 detection in chest X-ray images, achieving 93% F1 score. Conducted systematic benchmarking by re-implementing 4 existing models on standardized datasets and published research in IEEE conference proceedings.

Grade: 3.6

Activities and societies: Dale Carnegie Program

M.Eng. in Artificial Intelligence & Data Science with a thesis on Autonomous Vehicle Guideway. Achieved a GPA of 3.6, placing in the top 3%.

Earned the AWS Machine Learning – Specialty certification in 2023.

Earned the AWS Certified Cloud Practitioner certification in 2023.

Earned the Azure AI Fundamentals certification in 2023.

Certified as a Software Engineer by Manara in 2022.

Completed the Advanced Data Analysis course from Udacity in 2021.

Grade: 3.5

Activities and societies: ENACTUS, MUN, NU Research Forum

B.Sc. in Computer Science with a thesis on Mental Health Support Mobile App. Achieved a GPA of 3.5, placing in the top 1%.

Participated in an exchange program at the University of Applied Sciences, Upper Austria from March to September 2019.