guillaume fradet profile picture

Hello!

I'm Guillaume, a french research engineer specializing in Artificial Intelligence and Deep Learning.
In 2019, I graduated from ESILV Engineering School and obtained a Master 2 degree in Data Science from École Polytechnique. Sensitive to the #AIforGood movement, I sought to apply my skills in the medical field. I then embarked on a research internship where I compared various approaches to classify tumors using MRI images and radiomic data. It was a good experience, but that remained too academic. I wanted to join a project with the ambition to use these technologies to revolutionize current practices. This is how I began my adventure at the young Parisian startup AZmed. Our goal was to assist doctors (radiologists and emergency physicians) in analyzing their ever-increasing volume of medical imaging while staffing levels remained stagnant. I joined a team of 6 people in a global context where no AI had ever been deployed in a medical center. We were the first to do so in France, with the software Rayvolve, which enables fracture detection on radiographs. For 4 years, I contributed to developing, improving, and expanding the scope of analysis of the algorithms. Clinical studies showed a real gain in time and precision when comparing a doctor alone to a doctor assisted by Rayvolve.
By the end of 2023, Rayvolve had grown to be used in routine clinical practice across over 500 medical centers in 50 countries - a significant achievement for our small team. After this rewarding journey, I felt it was the right time to pursue a long-held dream of mine: taking several months to travel and gain new perspectives.
Now back, I am ready for a new challenge that pushes the boundaries of what's possible with AI!

Experience


  • azmed

    Deep Learning Researcher

    AZmed, Paris

    November 2019 - November 2023
    • Development and continuous improvement of 2 certified algorithms to detect abnormalities on X-rays:
      • Trauma algorithm (CE & FDA): detecting fracture, dislocation, and effusion on any body part
      • Chest algorithm (CE): detecting consolidation, pleural effusion, cardiomegaly, pneumothorax, and pulmonary nodules
    • Research focus: Object Detection, Domain Adaptation/Generalization, Semi-supervised learning, Continual Learning
    • Company growth: One of the first employees. From 0 to 500+ healthcare centers in production. From 3 to 30+ employees.
    • MLOps responsibilities: Integration of the models into Rayvolve software (i.e. code of the inference), defining and developing the deployment process, AWS cost optimization.
    • Code owner, responsible for PR reviews in the AI team.
    • Cross-department collaboration: Served as the point of contact in the AI team for the Dev and Ops. Involved in product choices, HR processes (recruitment, onboarding, culture), and AI training for Business and CS teams.
    • Technologies used: Python, PyTorch, AWS, Docker.
    • Article (Medium): Domain Adaptation: the key to deploy algorithms on a large scale
  • capgemini

    Data Scientist (intern)

    Capgemini Engineering, Vélizy-Villacoublay

    April - September 2019
  • softbank-robotics

    Full Stack Developer (intern)

    SoftBank Robotics Europe, Paris

    April - August 2018
    • Developed a web-app archiving system for NAO and Pepper robot test data.
    • Application: "A.S.T.R.", a RESTful API-based web application, deployed across SoftBank Robotics.
    • Open Source: Application and Python library available on the company's GitHub.
    • Key Responsibilities:
      • Specification elaboration
      • Technology selection
      • Web application development (API and website)
      • Python library development
      • Managing the sending of large files to the server
      • User management
      • Advanced archive search
      • Deployment management
    • Technologies used: Node.js, MongoDB, Express, Python, Git, Docker, Ansible
    • Source code: the web application and the Python library
    • Article: Internship at SoftBank Robotics: Guillaume, Engineering Student Class of 2019, Full Stack Developer (ESILV)
  • fishfriender

    Developer (intern)

    Fishfriender, Paris

    June - July 2017
    • Automated the data retrieval and processing from partners.
    • Inserted the adapted data into the application's database.
    • Handled data from Excel spreadsheets and web pages using web scraping.
    • Technologies used: Node.js, JavaScript, SQL, JSON

Education


  • polytechnique

    Master 2 - Data Science

    École Polytechnique, Paris

    2018 - 2019
    • Advanced topics in Machine Learning (by Florence d'Alché Buc)
    • Advanced Learning for Text and Graph Data (by Michalis Vazirgiannis)
    • Deep Learning (by Charles Ollion & Olivier Grisel)
    • Reinforcement learning (by Erwan Le Pennec)
    • Optimization for Data science (by Alexandre Gramfort & Robert Gower)
    • Introduction to Graphical Models (by Umut Şimşekli)
    • Big Data Framework (Hadoop, Spark, ES) (by Salim Nahle)
    • Systems for Big Data Analytics (by Yanlei Diao)
    • Visualization and Visual Analytics for Data Science (by Jean Daniel Fekete)
    • Data Stream Processing (by Raja Chiky & Jérémie Sublime)
    • Machine Learning, Business case (by Nicolas Eid & Cyril Veron)
    • Big data & insurance (by Denis Oblin)
    • Data infrastructure (NoSQL) (by Nicolas Travers)
    • Mixed Effects Models for the Population Approach (by Marc Lavielle)
    • Big Data camp (by Alexandre Gramfort & Balazs Kegl)
  • esilv

    Master of Engineering

    ESILV, Paris - La Défense

    2014 - 2019
    • Major: Computer Science, Big Data and connected objects
    • Activities and associations: Member and Communication Manager of the robotics association DaVinciBot (participated in the French Robotics Cup 2016 and 2017).
    • Example of the classes followed:
      • Machine Learning and clustering
      • Mobile application development
      • Web Application Architectures
      • Adv topics in NoSql databases
      • Embedded Systems: architecture & programming
      • MVC: interfaces and data
      • Inferential statistics
      • Numerical analysis
      • SQL Database
      • Signal processing
  • louisiana-tech-university

    Exchange program

    Louisiana Tech University, USA

    2017 (Fall semester)
    • Major: Computer Science
    • Courses:
      • Adv data structures & algorithms
      • Software design & engineering
      • Computer Networks
    • GPA: 4.0 (A)
    • Article about my experience

Portfolio



Domain Adaptation

The key to deploy algorithms on a large scale

A powerful detection algorithm for one medical center, but unsuitable for another. This is one of the major problems faced by research teams wishing to deploy their models on a large scale. In this article, I introduce this challenge called Domain Adaptation in the context of medical imaging, based on my experience at AZmed.

Read More

Predict lipomatous soft tissue tumors malignancy on MRI

Radiomics vs. Deep Learning

Research report comparing two main approaches - Radiomics and Deep Learning - to detect malignant soft tissue tumors directly on magnetic resonance imaging.

Read More

  • Guillaume Fradet
  • July 2019

MRI brain tumor dataset

Data downloading & loading

Utilities to download (CLI) and load an MRI brain tumor dataset with Python, providing 2D slices, tumor masks and tumor classes.

Read More

  • Guillaume Fradet
  • December 2018

Computer Vision: Mars craters

Object detection / segmentation

Application of object detection / segmentation (MaskRCNN and RetinaNet) on Mars satellite images. The goal was to detect automatically craters.

Read More

Reinforcement Learning

Q-Learning implementation

Implementation of the reinforcement learning technique Q-Learning. The environment was MountainCar (OpenAI Gym), where the goal is to teach a car to swing from left to right so that it can climb the mountain.

Read More

Skills


Programming

  • Python # Numpy, Pandas, Scikit-Learn, PyTorch, TensorFlow, Keras, Matplotlib
  • Web development # HTML, CSS, JavaScript, jQuery, Node.js, Express.js
  • Databases # SQL (MySQL, PostgreSQL), NoSQL (MongoDB), ElasticStack
  • C# / Java
  • R

Software / Tools

  • Git
  • Jupyter
  • LaTeX
  • Unix
  • RStudio
  • VS Code
  • Android Studio
  • Adobe Photoshop

Languages

  • 🇫🇷 French # native
  • 🇬🇧 English # fluent
  • 🇪🇸 Spanish # basic

Interests


Traveling 🌍

Probably the most cited "interest" in people's resumes, and I'm no exception. It may sound cliché but I really like being out there, discovering new places.
My type of travel is all about adventure. I dedicated 2024 to traveling around the world. Key destinations included South America (from Lima to Ushuaia without flying), French Polynesia, New Zealand, Japan, and Southeast Asia (see more here).
Previous adventures include a 1-month motorcycle tour of France and a 16-day trek in the Everest region.

Outdoor sports ⛰️

  • Climbing 🧗‍♂️
  • Hiking 🥾
  • Running 🏃‍♂️
  • Alpinism (easy stuff) ⛏️
  • Skiing (touring) / Snowboarding 🎿
  • Scuba diving 🤿

Contact