Júlio Arend

Software Engineer

Bavaria, Germany
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
🎓
Top School
Júlio Arend is a software engineer and Engineering Science student at TUM with five years of practical experience bridging mechanical engineering, automotive technology, and machine learning. He contributes to open-source forecasting tools like NeuralProphet, where he improved missing-data handling and conditional seasonality—skills that reflect both data-science rigor and production-oriented engineering. Bilingual and internationally minded, Júlio pairs analytical problem-solving with cross-cultural collaboration, having academic ties to UFRJ and research exposure at Stanford in energy forecasting. Currently seeking a company to host his bachelor’s thesis, he combines hands-on implementation, refactoring discipline, and an entrepreneurial interest in electromobility and innovation.
code5 years of coding experience
bookBachelor of Science - BS, Engineering Science, Bachelor of Science - BS, Engineering Science at Technische Universität München
bookMaschinenbau, Maschinenbau at Universidade Federal do Rio de Janeiro
languagesGerman, Spanish, French, Portuguese, English
github-logo-circle

Github Skills (14)

neural-network10
data-preprocessing10
forecasting10
machine-learning10
pytorch10
forecast10
time-series10
deep-learning10
python10
pytest9
testing9
autoregressive-models9
pandas9
vector-autoregression9

Programming languages (2)

Jupyter NotebookPython

Github contributions (5)

github-logo-circle
ourownstory/neural_prophet

May 2022 - Jan 2023

NeuralProphet: A simple forecasting package
Role in this project:
userData Scientist / ML Engineer
Contributions:27 reviews, 47 commits, 49 PRs in 8 months
Contributions summary:Júlio made significant contributions to the `neural_prophet` repository, focusing on enhancing the model's handling of missing data and improving its forecasting capabilities. They implemented features to allow for the imputation and dropping of missing values, addressing issues related to data preprocessing. Moreover, the user was involved in bug fixes and refactoring of plotting functions and enabling more features such as conditional seasonality.
forecastingneuralprophetpythonforecasttime-series
judussoari/neural_prophet

Apr 2022 - Jan 2023

NeuralProphet: A simple forecasting package
Contributions:3 PRs, 163 pushes, 48 branches in 9 months
pytorchforecastingneuralprophetpythondeep-learning
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.
Request Free Trial