Nassim Louissi

Nassim Louissi

ML Research Engineer — Paris

Published in Cornea & BJO. Production clinical AI at Quinze-Vingts Hospital. Medical device reverse engineering. Bare-metal x86/KVM. Georgia Tech MS CS starting January 2027. CatBoost fan.

I design and operate the MLOps infrastructure at Quinze-Vingts Hospital — one of Europe's leading ophthalmology centers — providing clinicians with 24/7 AI-assisted diagnosis. The system integrates heterogeneous data sources (corneal topographers, biomechanical analyzers, clinical records), applies the necessary mathematical transformations to make that data ML-ready, and serves predictions that feed directly into treatment decisions. I'm responsible for the full pipeline: from raw device exports to production-grade model serving.

I came to ML through an unusual path: a Bachelor's in Economics at Paris-Est Créteil, where I got hooked on econometrics and statistical modeling, followed by a Master's in Econometrics and Statistics at the University of Angers. The transition from economic forecasting to production ML systems turned out to be more natural than you'd expect — the core problems (noisy data, small samples, high stakes, real-time constraints) are the same.

Zernike wavefront analysis Medical device reverse engineering Corneal optics Bare-metal x86 Python PyTorch Docker/K8s

Experience

Machine Learning Engineer — Quinze-Vingts Hospital, Paris
April 2024 – Present (initially joined as intern)
  • Architecting and operating a full MLOps infrastructure for 24/7 AI-assisted clinical diagnosis, integrating data from MS-39, Corvis-ST, and clinical databases (~150k exams).
  • Built automated data pipelines: polar-to-cartesian coordinate conversion, Zernike polynomial extraction, biomechanical feature engineering — 4,000+ features computed at 5× speed (30 samples/min), with 2–6% deviation from manufacturer software.
  • Trained and deployed predictive models (ResNet, ViT, CatBoost) in Python/PyTorch — 97% accuracy on 1,000 samples, 100% classification on 120 surgical cases vs. 75% baseline, saving €70k–120k/year in avoided unnecessary procedures.
  • Deploying models with Docker/Kubernetes; collaborating directly with clinicians on validation and production integration.

Current Projects

mini-hypervisor — Bare-metal x86 execution inside KVM. Writing raw machine code to explore matmul algorithms on virtual hardware with zero OS abstraction.

GitHub

CorneaNet-AI — Reverse engineering the MS-39 corneal topographer. Polar-to-Cartesian reconstruction, Zernike decomposition, and investigating ray tracing methods to improve early keratoconus detection beyond the current clinical gold standard (Belin/Ambrosio).

GitHub

ISA deep dives — Working through the Intel 64 and IA-32 Software Developer's Manual, implementing random instructions in Rust. Exploring AVX-512 and AMX tile matrix operations.

Publications

Perez E*, Louissi N*, et al. "Machine Learning Model for Predicting Visual Acuity Improvement After Intrastromal Corneal Ring Surgery in Patients With Keratoconus." Cornea, 2025. Co-first author
Borderie VM, Georgeon C, Louissi N, Memmi B, Hamrani M, Bouheraoua N, Chessel A. "CorvisST biomechanical indices in the diagnosis of corneal stromal and endothelial disorders: an artificial intelligence-based comparative study." British Journal of Ophthalmology, 2025.