Thesis @ AI Medical AG · Research Assistant @ University of Neuchâtel
> building intelligent systems

Abdelrahman Faqieh

AI Engineer

LLMs Generative AI Computer Vision Segmentation

Bern, Switzerland

INPUT HIDDEN 1 HIDDEN 2 OUTPUT LLM text CV vision AI core GEN synth SEG med ŷ1 class ŷ2 pred ŷ3 gen NEURAL NETWORK

About Me

I design and build deep learning systems across research and industry. Currently pursuing my Master's in Artificial Intelligence in Medicine at the University of Bern.

My most significant work to date is PRISM, a generative AI framework I developed and co-authored for class-consistent image generation directly from structured tabular data, bypassing the language bottleneck in CLIP-based diffusion models. The work is under review at NeurIPS 2026 and achieves up to +116% improvement in class consistency over language-based baselines, with emergent geometric properties in the conditioning space arising without explicit supervision.

Alongside that, I've built vision-language architectures that outperform published baselines on zero-shot histopathology classification across seven public datasets, worked on brain lesion segmentation for longitudinal MRI in a clinical software product, and developed 3D path planning systems for autonomous underwater robotics. I enjoy tackling hard problems with intelligent systems and bringing research ideas all the way to working implementations.

4+
Work Experiences
3+
Research Projects
4
Languages Spoken

Work Experience

Machine Learning Researcher

AI Medical AG - Master's Thesis

Zurich, Switzerland Mar 2026 – Present

Developing and benchmarking state-of-the-art deep learning architectures for brain lesion segmentation in longitudinal MRI scans and integrating the selected architecture into the company's Jazz software to enable automated lesion detection and progression tracking across patient follow-up studies.

Deep Learning Medical Imaging Segmentation

AI Intern

Institute of Tissue Medicine and Pathology

Bern, Switzerland Nov 2025 – Apr 2026

Extended an existing vision-language framework by fine-tuning vision and language encoders on histopathology images and textual annotations, aligning their representations via contrastive loss for unsupervised downstream classification.

Vision-Language Models Contrastive Learning Hugging Face PyTorch
View Project ↓

Software Engineer (Part-time)

ARIS Space

Zurich, Switzerland Jun 2025 – Dec 2025

Developed a ROS 2 node in Python for 3D trajectory generation and geometric path planning for the Nautilus autonomous underwater glider, computing turn radii, pitch angles, and waypoints.

ROS 2 Python Path Planning Robotics

Biomedical Engineering Intern

Medical Park Goztepe

Istanbul, Turkey Jan 2024 – Feb 2024

Diagnosed and repaired electrical circuits in medical devices to improve functionality and reliability. Monitored equipment performance and identified potential failures to ensure seamless operation.

Medical Devices Circuit Diagnostics Biomedical Engineering

Publications

NeurIPS 2026 · Under Review Under Review

PRISM: Class-Consistent Image Generation from Tabular Data

Faqieh, A., Sánchez-González, S., Shankar, A., Chen, L.Y.

Tabular Metadata (structured attributes) CLIP / Language class bottleneck structurally fails PRISM Class-Consistent Image Generation Framework Stage 1: Per-attribute conditioning Stage 2: Contrastive refinement Inference: Classifier-free guidance HAM10000 Medical skin lesions 0.73 ≈ PLIP CUB-200-2011 Fine-grained birds 0.96 vs 0.83 PlantVillage Plant disease 0.93 +116% EMERGENT PROPERTIES Foreground localisation · IoU 0.63 Coherent class interpolation Zero-shot compositional transfer (no explicit supervision)

Proposed a diffusion-based framework for generating fine-grained, class-consistent images directly from structured tabular data, bypassing the language bottleneck inherent in CLIP-based conditioning. Designed a two-stage training pipeline and inference strategy. Outperformed language-based baselines across three benchmarks: 0.96 on CUB-200 (vs. 0.83 FT-CLIP), 0.93 on PlantVillage (+116% vs. FT-CLIP), and matched Specialized CLIP on HAM10000 (0.73) using only structured metadata with no domain-specific pretraining. Discovered emergent geometric properties in the conditioning space without explicit supervision.

Paper under review — details withheld pre-publication
Stable Diffusion Tabular Conditioning Generative AI Class Consistency NeurIPS 2026

Projects & Research

Input DINOv2 Spatial Tokens CROSS-ATTN Transformer Decoder Output A dog catching a frisbee in a park BLEU Score Evaluation RNN → LSTM → Transformer v1 v2 v4 v6

Image Captioning with Transformers and DINOv2

Developed six progressively improved models to generate captions for images. Used pretrained DINOv2 encoders and evolved decoders from RNNs to Transformers with cross-attention over spatial tokens. Evaluated with BLEU scores and visualized attention maps.

Transformers DINOv2 Computer Vision NLP
Sensor Data Feature Extraction ML Model A+ Quality Real-time Pipeline

WiiFit Exercise Quality Detection With Machine Learning

Designed and implemented a real-time machine learning pipeline for exercise quality assessment using WiiFit sensor data, including feature extraction, model training, and performance evaluation in a team-based setting.

Machine Learning Sensor Data Real-time Signal Processing

Technical Skills

Programming Languages

Python C++ C Matlab R

Deep Learning

PyTorch Scikit-Learn Hugging Face LangChain timm

Computer Vision & NLP

OpenCV Open3D SimpleITK spaCy NLTK

Data & C++

Pandas NumPy Matplotlib Seaborn STL Eigen OpenMesh

Tools & Infrastructure

Git Docker Slurm Weights & Biases Metashape Blender

Languages

English (Native) Arabic (Native) Turkish (B2) German (A2)

Education

M.Sc.

Artificial Intelligence in Medicine

University of Bern

Bern, Switzerland · Sep 2024 – Sep 2026

Deep Learning, Machine Learning, Computer Vision, From NLP to LLMs, Modeling & Scaling of Generative AI Systems, Reinforcement Learning, Trustworthy AI, HPC & Cloud Computing, C++ Programming

B.Sc.

Biomedical Engineering

Bahcesehir University

Istanbul, Turkey · Sep 2020 – July 2024

Principles of AI, Linear Algebra, Differential Equations, Signals and Systems, Programming in Python & C, Biostatistics, Medical Imaging & MRI, Modeling and Simulation

Honors Graduate

Honors & Awards

Honors Graduate - Graduated with Honors in Biomedical Engineering from Bahcesehir University
Koc University Summer Academy - Pass with Distinction in Life Sciences Course

Get in Touch

I'm always open to discussing new opportunities, research collaborations, or interesting projects. Feel free to reach out!