Guillaume Androz is a Senior Data Scientist based in Quebec with eight years of industry experience applying ML and signal processing to insurance, healthcare, and embedded systems. With a PhD in physics and a background in optics and fiber lasers, he blends rigorous research skills with practical software engineering in Python, C/C++, and cloud DevOps. He has built ECG analysis pipelines and production-ready deep learning models (PyTorch, TensorFlow/Keras) and contributed to open-source projects for time-series clustering and TensorFlow ASR, notably integrating a SentencePiece featurizer for speech recognition. Comfortable moving models from R&D into robust production, he also brings domain knowledge in measurement algorithms and qualification software from telecom test systems. Colleagues rely on him for bridging complex signal-processing theory and scalable ML solutions in regulated industries.
8 years of coding experience
6 years of employment as a software developer
Ph.D., Physics, Optics, Fiber Laser science, Ph.D., Physics, Optics, Fiber Laser science at Université Laval
BS, Optique Opto-Electronique et microondex, BS, Optique Opto-Electronique et microondex at Grenoble INP - Phelma
Msc, Physique des composants, micro- opto- electroniques, Msc, Physique des composants, micro- opto- electroniques at Institut national polytechnique de Grenoble
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2. Supported languages that can use characters or subwords
Role in this project:
ML Engineer
Contributions:2 reviews, 26 commits, 4 PRs in 1 month
Contributions summary:Guillaume primarily contributed to the project by integrating and implementing the SentencePiece featurizer. This involved adding the SentencePiece library as a requirement, creating a `SentencePieceFeaturizer` class, and integrating it into training and testing scripts. The changes demonstrate a focus on text processing and vocabulary management for automatic speech recognition models.
The machine learning toolkit for time series analysis in Python
Role in this project:
ML Engineer
Contributions:6 commits, 1 PR, 9 comments in 3 months
Contributions summary:Guillaume primarily contributed to the implementation and improvement of machine-learning algorithms within the tslearn library, specifically focusing on clustering techniques like k-Shape and k-Means. Their work involved adding features for initial centroid/guess specification, refining preprocessing efficiency, and modifying existing functions. The commits demonstrate a clear understanding of time series analysis and clustering concepts, with the goal of enhancing the flexibility and performance of the library's algorithms.
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.