👋 Hi, I'm Paul Peyssard, a passionate Machine Learning Engineer & Data Scientist working on cancer & brain deases

• Data Scientist at Neuro-Sys - Image analysis automation and deep learning for Brain deseases (Computer vision) & LLM
• Internship at Veracyte - Applied my AI skills in a real-world healthcare setting, practicing cancer diagnosis and processing Whole Slide Images
• Internship at Airbus Helicopters - Different applications, and models such as Anomaly Image Detection on helicopter's main gear boxes
• Research project with IBM - Contributed to improving ML models using IBM's Deep Neural Network, R2N.

• Master 2 in Artificial Intelligence & Machine Learning (Centrale Méditerannée - Aix-Marseille University) - Focusing on cutting-edge AI research and applications.
• International Master 1 in Artificial Intelligence & Data Science (Côte d'Azur University) - Focusing in the basis of Machine learning, Deep learning & statistics
• B.Sc. in Computer Science (Aix-Marseille University) - Clean code, algorithms, databases and different languages.

• Personal Freelance Website – Custom freelance portfolio website built with Next.js and Tailwind CSS, featuring responsive design and dynamic content.
• Neuro-Sys - LLM (Confidential) - Deployed a Mixtral-based RAG pipeline using LangChain on AWS infrastructure to provide secure and contextual access to internal data supporting both biologists and financial department
• Neuro-Sys - Bran cell anomaly detection (Confidential) - Brain Whole Slide Image Segmentation using different models (Stardist, Detectron...)
• Neuro-Sys - Web application (Confidential) - Developed different web applications to automate image and file analysis using Python, Flask, and Waitress.
• Veracyte - Data Augmentation Projects (Confidential) - Whole Slide Image Data Augmentation & Normalization (Bioinformatics - Deep Learning)
• Airbus - Main Gear Box Anomaly Detection (Confidential) - Detection of different anomaly (Fretting, corrosion...) on helicopters main gear boxes (Image anomaly detection)
• Airbus - Fuel Flow Prediction (Confidential) - Prediction of fuel flow consumption on helicopter's takeoff
• Projet PSTALN - Comparaison of Pre-trained transfomers and home-made transformers on POS tagging
• Projet SAM - Multi-Modal Turn-To-Speak deep learning model detection using speech, sound and videos (Comparaison of early and late fusion)
• Molecule Generator - Molecule generation using constraint programming (COP) in collaborations with chemist (Research Project)
• Pet Adoption Prediction - Utilizing ML algorithms to predict pet adoption rates.
• Word2Vec Implementation - Building the Word2Vec Skip-gram model from scratch for natural language processing tasks.
• Learning Compact Transparent Models using Neuro-Symbolic Methods - Research project aimed at enhancing ML models' efficiency and transparency.
• Statistics Projects 2022 - A series of projects exploring statistical analysis methods.

• Neural Network Optimization
• BioInformatics and Whole Slide Image processings
• Finance Optimization & Fraud Detection using Deep Learning

• LinkedIn: Paul Peyssard
• Email: paul.peyssard@gmail.com

• AI in Video Games, Healthcare & Finance
• Ethical AI
• Open Source Contribution
• Sports & Cooking

Thank you for visiting my profile! Feel free to explore my repositories and reach out if you have any questions or collaboration ideas.