Guillaume Chevalier
Senior Software Developer at helloDarwin
Greater Montreal Metropolitan Area Canada
Summary
🤩
Rockstar🎓
Top SchoolGuillaume Chevalier is a Senior Software Developer with 11 years of experience specializing in deploying production-grade AI and deep learning systems across security, industry 4.0, and startup environments. He has led end-to-end ML projects from research to production—productizing generative AI services at Secureworks and building B2B ML offerings as Machine Learning Director at Neuraxio—deploying at least seven AI services to production. Comfortable across TensorFlow-based sequence and LSTM models (see his open-source human activity recognition and seq2seq signal forecasting work), he blends hands-on model engineering with scalable, secure service design. Known for rapid prototyping—often winning internal hackathons and turning prototypes into widely adopted products—he also secures research funding and navigates cross-functional stakeholder needs. Based in Greater Montreal, he pairs strong academic foundations in software engineering with practical experience in C++, cloud, and applied research.
11 years of coding experience
7 years of employment as a software developer
Bachelor’s Degree Software Engineering, Bachelor’s Degree Software Engineering at Université LavalNatural Sciences with additional classes picked in: Mathematics and Computer Science, Natural Sciences with additional classes picked in: Mathematics and Computer Science at Cégep de Sainte-FoyHigh School Information Technology, High School Information Technology at Les Compagnons-de-CartierInternational (Bilateral) Profile (a.k.a. Bachelor exchange studies) CSE, International (Bilateral) Profile (a.k.a. Bachelor exchange studies) CSE at Linköping University
French, English
Stackoverflow
10,198reputation
4.8mreached
97answers
64questions
integer
top-5%
neural-network
top-5%
machine-learning
top-5%
git
top-5%
scikit-learn
top-5%
python
top-5%
Github Skills (25)
python10
machine-learning10
rnn-model10
recurrent-neural-networks10
n10
seq2seq10
numpy10
deeplearning-ai10
lstm10
deep-learning10
tensorflow10
neural-network10
cuda10
git9
linux9
Programming languages (15)
Github contributions (5)
guillaume-chevalier/LSTM-Human-Activity-Recognition
May 2016 - Nov 2022
Human Activity Recognition example using TensorFlow on smartphone sensors dataset and an LSTM RNN. Classifying the type of movement amongst six activity categories - Guillaume Chevalier
Role in this project:
ML Engineer
ML EngineerContributions:27 commits, 2 PRs, 22 pushes in 6 years 6 months
Contributions summary:Guillaume's primary contribution involves building and training a TensorFlow-based LSTM neural network for human activity recognition. They implemented a data acquisition script, improved documentation, and made small edits to improve the presentation of the model, which included changes in hyperparameters like the learning rate, as well as refactoring some components. The user also updated the codebase to TensorFlow version r0.10 and implemented a stacked LSTM architecture with L2 loss.
sensorssmartphone-sensorstype-oftensorflowrnn
guillaume-chevalier/seq2seq-signal-prediction
Mar 2017 - Nov 2022
Signal forecasting with a Sequence-to-Sequence (seq2seq) Recurrent Neural Network (RNN) model in TensorFlow - Guillaume Chevalier
Role in this project:Data Scientist
Data ScientistContributions:47 commits, 2 PRs, 15 pushes in 5 years 8 months
Contributions summary:Guillaume implemented a sequence-to-sequence (seq2seq) recurrent neural network (RNN) model using TensorFlow for time series forecasting. The code initializes and trains the model, incorporating loss functions, optimizers, and batch processing. The user appears to have experimented with different training parameters and datasets, as evidenced by the changes in the code. The primary focus of the user's work is on building and training a machine learning model for signal prediction within a given time series data context.
forecastingsequencernnpythonsignal
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.