Sep 2025-Dec 2025
AI Computer Vision Engineer | Stealth Start-Up
Evaluated vision and generative AI foundation models on large-scale image/video datasets, fine-tuned VLMs in PyTorch for animation movies.
Raluca-Maria Sandu
AI/ML Researcher and Engineer · Zurich, Switzerland
I am an applied AI/ML engineer with around 20 years of coding experience, strong in communication, collaboration and mentoring . My industry work has mostly focused on visual AI, building systems that classify, understand, generate and reason about images and videos. During my PhD in Biomedical Engineering, I worked in European hospitals on medical imaging research for liver cancer, which led to journal publications and contributions to a commercial product deployed in hospitals. My current technical curiosity is physical AI: how machines can understand, navigate, and interact with our messy, beautiful 3D world. That interest also connects deeply with my life outside work: I love hiking, surfing, skiing, snowboarding, gardening, and birdwatching (currently taking ornithology classes). For me, AI is most exciting when it helps us perceive, understand, and protect the real world around us.
Experience & education
2022-2025
Machine Learning Team Lead | Accenture
Led machine learning and generative AI work across applied research, engineering, and client-facing delivery.
2017-2022
PhD Biomedical Engineering | University of Bern
Researched image-based efficacy analysis and predictive modelling for liver tumour ablation treatments.
2016-2017
Graduate Master's thesis project | Philips Research
Completed my Master's thesis on image segmentation and semantic description, implementing skin structure segmentation and classification algorithms that achieved 98% accuracy with Random Forests.
2014-2016
MSc Biomedical Engineering | RWTH Aachen University
Completed graduate studies in biomedical engineering with a focus on imaging, analysis, and computational methods.
2010-2014
BSc Applied Computer Science | Bucharest, Romania
Completed a Philips Research thesis on volumetric capnography respiratory signals, applying MATLAB time series analysis and ML algorithms that achieved 90% respiratory disease classification accuracy.
Recent work
Featured blog projects
April 18, 2025
Segmentation of Fine Facial Wrinkles with U-Net
Segmenting wrinkles is still unsolved task with many applications
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 Evaluatio...
August 19, 2024
Generative AI Image Tools in Marketing and Design: Opportunities & Challenges
GenAI software & tools in image generation & editing for (mostly) non-technical users.
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...
June 15, 2024
Fine-tuning with Stable Diffusion XL
Fine-tuning your own images with Stable Diffusion XL - Just another project with my cats
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 avai...
April 04, 2024
Prompts, tips, tricks for photography with Midjourney
Creating incredibly realistic photos with Midjourney
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 a...