Long Yu
R&D Lead at Wide eyes technologies
Greater Barcelona Metropolitan Area Spain
Summary
👤
Senior🎓
Top SchoolLong Yu is an R&D lead and computer vision specialist with 11 years of experience building biometric pattern analysis, visual object tracking, large-scale image retrieval and detection systems. As co-founder and Head of Research at Wide Eyes Technologies and now leading R&D at Stylitics in Greater Barcelona, he bridges deep research rigor with product-focused engineering. His background blends a Master in Computer Vision and AI with hands-on roles from academic labs to industry, including soccer player tracking and HCI projects. An active contributor to open-source ML tooling, he improved the FreqAI module of the popular freqtrade crypto bot by enhancing CatBoost integration, data pipelines and feature-weighting workflows. Known for turning complex vision models into production-ready components, he excels at scaling analytics for real-world applications.
11 years of coding experience
3 years of employment as a software developer
Master of Computer Vision and Artificial Intelligence Computer Vision, Master of Computer Vision and Artificial Intelligence Computer Vision at Universidad autonoma de barcelonaIngeniero Superior Procesado de señal, Ingeniero Superior Procesado de señal at Universidade de Vigo
Spanish, English, Italian, Chinese
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (12)
machine-learning10
cryptocurrencies10
python10
algorithmic-trading10
data-science10
fread10
numpy9
pandas9
catboost8
scikit8
scikit-learn8
data-engineering8
Programming languages (6)
Github contributions (5)
freqtrade/freqtrade
Jul 2022 - Aug 2022
Free, open source crypto trading bot
Role in this project:
ML Engineer & Data Scientist
ML Engineer & Data ScientistContributions:3 reviews, 10 commits, 8 PRs in 1 month
Contributions summary:Long primarily contributed to the FreqAI module within the project, focusing on improving documentation and implementing features related to model training and data handling. Their work included modifying the Catboost prediction model, updating data processing logic, and integrating functionalities for feature weighting and training date logging. The commits show a focus on improving and extending the FreqAI capabilities for use within the trading bot framework.
telegram-botalgorithmic-tradingpythonfreqtradetrading-bot
lolongcovas/EfficientDet.Pytorch
Mar 2020 - Apr 2020
Implementation EfficientDet: Scalable and Efficient Object Detection in PyTorch
Contributions:20 pushes in 18 days
pytorchscalableefficientnetdetectionobject-detection
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.