Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Hi, I’m Mehdi Hajoub, a Machine Learning & Image Analysis Engineer focused on medical imaging, model development, and statistical quality analysis. I apply Python, computer vision, and quantitative methods to evaluate the stability and reliability of biological and clinical data, and I’ve deployed robust, reproducible pipelines in healthcare environments such as CHUV and Campus Biotech. I’m passionate about using AI to support diagnostic workflows, including segmentation, classification, stain monitoring, and imaging QC. I thrive in interdisciplinary settings, translating clinical needs into scalable AI solutions and collaborating with clinicians, researchers, and engineers to drive impactful, validated deployments that improve patient care.…Hi, I’m Mehdi Hajoub, a Machine Learning & Image Analysis Engineer focused on medical imaging, model development, and statistical quality analysis. I apply Python, computer vision, and quantitative methods to evaluate the stability and reliability of biological and clinical data, and I’ve deployed robust, reproducible pipelines in healthcare environments such as CHUV and Campus Biotech. I’m passionate about using AI to support diagnostic workflows, including segmentation, classification, stain monitoring, and imaging QC. I thrive in interdisciplinary settings, translating clinical needs into scalable AI solutions and collaborating with clinicians, researchers, and engineers to drive impactful, validated deployments that improve patient care.

MEHDI HAJOUB

Data Scientist, Web Developer, Front-End Developer, +5





Hi, I’m Mehdi Hajoub, a Machine Learning & Image Analysis Engineer focused on medical imaging, model development, and statistical quality analysis. I apply Python, computer vision, and quantitative methods to evaluate the stability and reliability of biological and clinical data, and I’ve deployed robust, reproducible pipelines in healthcare environments such as CHUV and Campus Biotech. I’m passionate about using AI to support diagnostic workflows, including segmentation, classification, stain monitoring, and imaging QC. I thrive in interdisciplinary settings, translating clinical needs into scalable AI solutions and collaborating with clinicians, researchers, and engineers to drive impactful, validated deployments that improve patient care.…Hi, I’m Mehdi Hajoub, a Machine Learning & Image Analysis Engineer focused on medical imaging, model development, and statistical quality analysis. I apply Python, computer vision, and quantitative methods to evaluate the stability and reliability of biological and clinical data, and I’ve deployed robust, reproducible pipelines in healthcare environments such as CHUV and Campus Biotech. I’m passionate about using AI to support diagnostic workflows, including segmentation, classification, stain monitoring, and imaging QC. I thrive in interdisciplinary settings, translating clinical needs into scalable AI solutions and collaborating with clinicians, researchers, and engineers to drive impactful, validated deployments that improve patient care.

Available to hire

Hi, I’m Mehdi Hajoub, a Machine Learning & Image Analysis Engineer focused on medical imaging, model development, and statistical quality analysis. I apply Python, computer vision, and quantitative methods to evaluate the stability and reliability of biological and clinical data, and I’ve deployed robust, reproducible pipelines in healthcare environments such as CHUV and Campus Biotech. I’m passionate about using AI to support diagnostic workflows, including segmentation, classification, stain monitoring, and imaging QC.

I thrive in interdisciplinary settings, translating clinical needs into scalable AI solutions and collaborating with clinicians, researchers, and engineers to drive impactful, validated deployments that improve patient care.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

English

Fluent

Spanish; Castilian

Advanced

French

Fluent

Arabic

Fluent

German

Advanced

Italian

Beginner

Work Experience

Software Engineer at Resilient

February 15, 2024 - Present

Web developer at Studuo

February 23, 2025 - Present

AI Engineer at Le Tenseur

August 20, 2025 - Present

https://www.letenseur.com

Machine Learning Engineer Intern at Campus Biotech

January 1, 2025 - Present

Deployed a graph neural network system for neurodegenerative disease classification (12 disorders, 600+ fMRI scans), serving 15+ researchers with 99.2% uptime and sub-2-second inference latency. Built automated retraining pipeline with Airflow and Docker, reducing update cycle from quarterly to weekly and preprocessing time from 72h to 4h through stability-based feature selection (60% storage reduction).

Clinical ML & Data Pipeline Engineer at NeuroRestore (CHUV-EPFL)

September 1, 2023 - March 1, 2024

Built multimodal NLP system to objectively quantify rehabilitation progress in spinal cord injury patients: automated transcription of 40+ hours of therapy sessions with medical language embeddings, synchronized to neuro-stimulation parameters and EMG data to measure movement quality and correlate verbal commands with motor recovery. Engineered and deployed a production-grade clinical software application at CHUV integrating the full NLP pipeline; implemented containerized services (Docker) with optimized inference (INT8 quantization, batched processing) reducing end-to-end latency from 8.2s to 2.9s and enabling near-real-time use by therapists.

AI Project Developer at EPFL AI Center

February 1, 2024 - May 1, 2024

Developed real-time sign language recognition system (1K videos, 50K frames) using Temporal Transformer architecture with CTC decoder, achieving 91% accuracy at 30 FPS. Compressed model from 42M to 11M parameters via pruning and quantization while maintaining 88% accuracy with 3× faster inference, enabling mobile deployment.

Medical Image Analysis Researcher at EPFL LTS5 Lab

September 1, 2023 - January 1, 2024

Trained medical imaging models (ResNet-50, EfficientNet-B3) for cervical cancer detection on a 200-image dataset, achieving 93% accuracy with cross-hospital validation (Geneva ↔ Cameroon). Improved domain generalization by 18% and reduced critical false negatives by 22% through adversarial domain adaptation and hybrid supervision techniques.

Machine Learning Engineer Intern at Campus Biotech, Geneva

January 1, 2025 - Present

Deployed graph neural network system for neurodegenerative disease classification (12 disorders, 600+ fMRI scans) serving 15+ researchers with 99.2% uptime and sub-2-second inference latency. Built automated retraining pipeline with Airflow and Docker, reducing update cycle from quarterly to weekly and preprocessing time from 72h to 4h through stability-based feature selection (60% storage reduction).

Clinical ML & Data Pipeline Engineer at NeuroRestore (CHUV-EPFL), Lausanne

September 1, 2024 - December 31, 2024

Built multimodal NLP system to objectively quantify rehabilitation progress in spinal cord injury patients: automated transcription of 40+ hours of therapy sessions with medical language embeddings, synchronized to neuro-stimulation parameters and EMG data to measure movement quality and correlate verbal commands with motor recovery. Engineered and deployed a production-grade clinical software application at CHUV integrating the full NLP pipeline; containerized services (Docker) with optimized inference (INT8 quantization, batched processing) reducing end-to-end latency from 8.2s to 2.9s and enabling near–real-time use by therapists.

AI Project Developer at EPFL AI Center, Lausanne

February 1, 2024 - May 31, 2024

Medical Image Analysis Researcher at EPFL LTS5 Lab, Lausanne

September 1, 2023 - January 31, 2024

Trained medical imaging models (ResNet-50, EfficientNet-B3) for cervical cancer detection on 200-image dataset, achieving 93% accuracy with cross-hospital validation (Geneva ↔ Cameroon). Improved domain generalization by 18% and reduced critical false negatives by 22% through adversarial domain adaptation and hybrid supervision techniques.