Built a document-grounded RAG pipeline at OeNB.
A specialized chatbot workflow that grounds answers in an OeNB document collection and measures whether retrieval finds the right evidence.
Open case studyMohamed Ali / Applied AI Engineer
Retrieval systems, sequence-model ablations, and vision models — built, measured, and reported with the uncertainty left in. The digit classifier on the right is one of mine, written from scratch in C++.
MNIST digits were size-normalised into a 20×20 box and shifted so their centre of mass sits at the centre of the 28×28 field. Feed a raw stroke straight in (1) and the network reads the wrong distribution, so the drawing is cropped and rescaled (2), then translated by centre of mass (3). Step 3 is what the network actually sees.
Applied systems and controlled experiments, with the implementation and evidence kept visible.
A specialized chatbot workflow that grounds answers in an OeNB document collection and measures whether retrieval finds the right evidence.
Open case studyA capacity-matched study of two-block xLSTM, LSTM, and Transformer models on associative recall and formal-language tasks.
Open case studyA from-scratch image-restoration entry that placed fourth while training on an 8GB GPU.
Open case studyAn experimental comparison of model families, hyperparameters, acoustic representations, and evaluation criteria for bird-species recognition.
Open case studyTwo country maps compare 2018 HDI with the percentage of surveyed new coders living in cities of more than one million people.
Open case studyA handwritten-digit neural network implemented from first principles in C++ as a hands-on project for fun.
Open case studyAt OeNB, I worked on document processing, retrieval, language-model workflows, and retrieval evaluation for RAG systems.
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