João Vinagre
Scientific Project Officer at European Commission
Seville, Andalusia, Spain
Summary
👤
Senior🎓
Top SchoolJoão Vinagre is a research-focused Scientific Project Officer at the European Commission and an invited professor with 13 years’ experience at the intersection of recommender systems, online learning and AI. He combines academic rigor from a PhD in Computer Science with hands-on engineering—contributing incremental-update features and stability fixes to a .NET recommender library—bridging theory and production. Based in Seville, he has a track record across research labs and universities, leading projects on data streams and evaluation methodologies. Known for pragmatic solutions to online learning challenges, he brings both project leadership and low-level algorithmic implementation experience to interdisciplinary teams.
13 years of coding experience
23 years of employment as a software developer
Msc, Networked Systems Engineering, Msc, Networked Systems Engineering at DCC-FCUPPhD, Computer Science, PhD, Computer Science at Universidade do Porto
Github Skills (13)
algorithm10
data-structures10
algorithms10
machine-learning10
csharp10
dotnet-core10
data-structure10
recommender-system10
incremental-learning9
cosine-similarity9
asp-net9
dotnet9
net9
Programming languages (3)
Github contributions (5)
zenogantner/MyMediaLite
Nov 2012 - Jan 2013
recommender system library for the CLR (.NET)
Role in this project:
Back-end Developer
Back-end DeveloperContributions:13 commits in 2 months
Contributions summary:João primarily focused on enhancing the `mymedialite` recommender system library by implementing incremental update capabilities within the ItemKNN algorithm. Their work involved modifying the existing code to incorporate co-occurrence matrices and selectively retrain the nearest neighbor lists after adding or removing feedback. They also addressed various bugs, code style issues, and type conversion problems, contributing to the overall stability and efficiency of the recommender system's core functionalities.
dotnetrecommendercollaborative-filteringmachine-learningmatrix-factorization
joaoms/MyMediaLite
Mar 2015 - Feb 2021
Contributions:1 release, 196 pushes, 6 branches in 5 years 11 months
pythonrecommendermachine-learningpurposemulti-purpose
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.