Built a document-grounded RAG pipeline at OeNB.
A document-grounded AI workflow that treats retrieval, provenance, evaluation, and refusal as parts of one system.
Open case studyMOHAMED ALI / APPLIED AI ENGINEER
I build and evaluate retrieval, language, vision, and sequence-model systems—from document AI at OeNB to controlled xLSTM benchmarks.
Applied systems and controlled experiments, with the implementation and evidence kept visible.
A document-grounded AI workflow that treats retrieval, provenance, evaluation, and refusal as parts of one system.
Open case studyControlled experiments on hybrid xLSTM, LSTM, and Transformer blocks across associative recall and formal-language tasks.
Open case studyA deep recursive laplacian network reconstructing deliberately damaged regions in grayscale imagery.
Open case studyA multi-branch classifier combining Mel, MFCC, and engineered acoustic features for imbalanced bird-species recognition.
Open case studyA geographic comparison of human development and where new coders live within each country’s urban system.
Open case studyA feed-forward handwritten-digit classifier implemented from scratch in C++, reconstructed for the browser from its verified architecture.
Open case studyAt OeNB, I worked across the complete RAG path: document processing, retrieval, language models, evaluation, guardrails, and accessibility.
At JKU, I completed a Bachelor's in Artificial Intelligence and am continuing with a part-time Master's while building deeper experimental work.
Read the full profile