Robin Vaysse is a data scientist and PhD-trained audio processing researcher based in Toulouse with eight years of experience applying ML to real-world problems, from e-commerce R&D at Mirakl to clinical speech-intelligibility tools. He blends academic depth in pathological speech rhythm modeling with hands-on engineering—shipping mobile prototypes for emotion detection and integrating ML models into iOS apps. At Mirakl he focuses on improving platform experiences via language models and LLMs, while his open-source contributions include implementing online recommender components (online SVD, AMSGrad) for the widely used River library. Comfortable moving between research and production, he has tackled real-time transcription, noise reduction and 3D point-cloud segmentation during previous industry and research roles. Less obvious: he pairs statistical rigor from a Master in SID with practical deployment experience, making him effective at turning speech and audio research into scalable products.
8 years of coding experience
1 year of employment as a software developer
Master SID (Statistique et Informatique Décisionnelle), Mathematics and Computer Science, Master SID (Statistique et Informatique Décisionnelle), Mathematics and Computer Science at Université Paul Sabatier Toulouse III
Licence Mapi3 (Mathématiques appliquées à l'ingénierie, l'industrie et l'innovation), Applied Mathematics, Licence Mapi3 (Mathématiques appliquées à l'ingénierie, l'industrie et l'innovation), Applied Mathematics at Université Paul Sabatier (Toulouse III)
Contributions:34 commits, 12 PRs, 31 comments in 1 year 8 months
Contributions summary:Robin implemented and updated machine learning models within the `river` online machine learning library. Their contributions focused on recommender systems, specifically an online SVD implementation. The user also worked on initializers and AMSGrad optimizer and added tests to the normal predictor in the `reco` module. Furthermore, the user made multiple changes in the code base by updating and fixing minor bugs.
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.