PhD in biophysics · image analysis · quantitative microscopy · scientific software · AI-assisted workflows

I build tools that turn complex scientific images into reliable, measurable data.

My background is in biophysics and quantitative imaging, where I worked on extracting mechanical and morphological information from microscopy experiments. Over time, I became increasingly interested in the engineering side of science: building robust pipelines, automating analysis workflows, validating results, and turning research methods into reusable software.

Today, I work mainly at the intersection of:

🤖 Applied AI & automation
🔬 Scientific imaging
👁️ Computer vision
📊 Quantitative analysis
🛠 Reproducible software engineering

Image dataset quality-control toolkit for computer vision workflows.
Detects duplicates, blur, corruption, exposure issues and train/validation leakage. Exports HTML, JSON and CSV reports.

Scientific imaging package for extracting mechanical information from microscopy images.
Includes topology extraction, Bayesian force inference, curvature analysis and stress summaries.

Android computational photography prototype combining monocular depth estimation with GPU-based bokeh rendering.

Configurable PyTorch U-Net pipeline for biological image segmentation, with training, inference and validation examples.

• AI-assisted workflows using LLMs, APIs and automation to make scientific and technical work faster
• Image analysis pipelines for microscopy, biological imaging and visual datasets
• Computer vision tools for segmentation, tracking, registration and quality control
• Scientific software that turns research methods into reusable packages
• Data validation workflows with clear reports and reproducible outputs
• AI-assisted tools for scientific discovery and experimental analysis

Languages: Python · MATLAB · C++ · SQL
Image analysis: OpenCV · scikit-image · Fiji/ImageJ · segmentation · tracking · registration
Machine learning: PyTorch · TensorFlow · scikit-learn · U-Net · CLIP
Scientific computing: NumPy · SciPy · Pandas · modelling · optimization
Engineering: Git · Pytest · CI/CD · Docker · FastAPI · reproducible workflows

• Scientific imaging and quantitative microscopy
• Computer vision for biological and medical images
• Dataset quality control before ML training
• Inverse problems and physics-informed image analysis
• Tools that make experimental data more reliable and easier to use

Good scientific software should not only work once.
It should be understandable, testable, reusable, and useful to someone else.

📍 Strasbourg, France
🔗 LinkedIn