Raluca-Maria Sandu

I am an AI and machine learning engineer and researcher focused on solving real-world problems. My work spans computer vision, multimodal systems, and generative AI, with a particular interest in building practical solutions for complex image and language problems. I got my PhD in Biomedical Engineering from the University of Bern in 2022, where I developed medical imaging methods for improving the evaluation of liver cancer treatments. That work was later integrated into a commercial product at a Swiss medical device company. I then spent three years at Accenture, where I delivered AI solutions across different industries and worked at the boundary between research, engineering, and business needs. Across consulting and freelance work, I have built systems ranging from medical imaging pipelines to computer vision and multimodal AI applications on AWS cloud. I am based in Zurich, Switzerland. Outside work, I am happiest outdoors, whereas is surfing, skiing, snowboarding, gardening, or birdwatching. I care deeply about nature, animals, and environmental conservation.
Python PyTorch Machine Learning Deep Learning Computer Vision Medical Imaging Diffusion Models AWS Generative AI Project Management

Recent Blogposts

Segmentation of Fine Facial Wrinkles with U-Net

Segmenting wrinkles is still unsolved task with many applications

Posted on April 18, 2025

Table of Contents Introduction What are fine facial wrinkles and why are these so hard to classify? Model architecture Dataset Preparation and Augmentation Results and Evaluation Conclusi... Read More

Generative AI Image Tools in Marketing and Design: Opportunities & Challenges

GenAI software & tools in image generation & editing for (mostly) non-technical users.

Posted on August 19, 2024

This post has been written as part of my work at Accenture and can be found on LinkedIn as well. This blog post represents my personal views and subjective experience with these tools. I ... Read More

Fine-tuning with Stable Diffusion XL

Fine-tuning your own images with Stable Diffusion XL - Just another project with my cats

Posted on June 15, 2024

Late to the party as usual, I finally got around fine-tuning my own images with Stable Diffusion XL 1.0 on a free-tier Google Colab using LoRA. Despite many tutorials being available so f... Read More

Prompts, tips, tricks for photography with Midjourney

Creating incredibly realistic photos with Midjourney

Posted on April 04, 2024

To be honest, I was never interested in trying Midjourney - sure you can create cool pics, but what could I use them for? After all, I live in a small apartment, and our walls are already... Read More
View all blog posts