Eliot Andres
Co-Founder at Photoroom
Paris, Ile-de-France
Summary
🤩
Rockstar🎓
Top SchoolEliot Andres is a Paris-based co-founder and former CTO with 11 years of experience building production-grade computer vision and scalable ML systems for consumer-facing photo editing at PhotoRoom. He transitioned from leading engineering to an individual contributor role to focus on high-impact AI problems, bringing hands-on expertise in TensorFlow, large-scale image pipelines (100M+ images/month), and mobile inference (TensorFlow Lite/Core ML). Eliot has a strong engineering foundation from Télécom Paris and École des Ponts, and a track record of cost-efficient GPU training and production deployments that drove real-world product impact. His open-source contributions include fine-tuning CNN models in a Packt-published computer vision repo, reflecting practical model improvements like architectural tweaks to reduce overfitting. Equally comfortable architecting back-end systems handling billions of events and optimizing model pipelines, he blends startup leadership with deep implementation skills.
11 years of coding experience
3 years of employment as a software developer
Engineer's Degree Engineering, Engineer's Degree Engineering at Ecole Nationale des Ponts et ChausséesMaster’s Degree Computer Software Engineering, Master’s Degree Computer Software Engineering at Télécom ParisPost high school courses in pure sciences Physics Mathematics and Chemistry, Post high school courses in pure sciences Physics Mathematics and Chemistry at Lycée Pasteur and Lycée Condorcet
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (6)
mask-rcnn10
faster-rcnn10
machine-learning10
tensorflow10
python9
jupyter-notebook9
Programming languages (8)
Github contributions (5)
PacktPublishing/Hands-On-Computer-Vision-with-TensorFlow-2
Dec 2018 - May 2019
Hands-On Computer Vision with TensorFlow 2, published by Packt
Role in this project:
ML Engineer
ML EngineerContributions:27 commits, 6 PRs, 28 pushes in 4 months
Contributions summary:Eliot removed dropout layers and made other changes to the model. This likely involved adjusting the model architecture to improve performance or address overfitting. Their work focused on fine-tuning a Convolutional Neural Network (CNN) model used for image classification within the project, and also involves a modification of the training pipeline.
hands-onpythonvisiondeep-learninghands
EliotAndres/dotfiles
Jan 2016 - Oct 2020
Contributions:14 pushes, 1 branch in 4 years 9 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.