Dustin Brunner
Data & AI Engineer
Winterthur, Zurich, Switzerland
Summary
🤩
Rockstar🎓
Top SchoolDustin Brunner is a Data & AI Engineer based in Winterthur with four years of hands-on experience building production-ready time-series and forecasting solutions. At Unit8 he moved from intern to engineer, delivering a Palantir Foundry route-planning tool and driving major performance gains in the open-source Darts forecasting library—achieving up to 400x speedups through vectorized regression and adding autoregressive generation and tests. He combines applied ML research experience from a brief research assistantship at Oracle with practical client-facing delivery, improving forecasting accuracy and operational workflows across energy, manufacturing, and logistics. Trained at ETH Zürich in computer science, Dustin blends rigorous academic grounding with pragmatic engineering and a demonstrated knack for turning slow prototypes into fast, maintainable systems.
4 years of coding experience
1 year of employment as a software developer
Matura, Matura at Kantonsschule Im LeeKantonsschule RychenbergMaster of Science ETH, Computer Science, Master of Science ETH, Computer Science at ETH ZürichBachelor of Science ETH, Computer Science, Bachelor of Science ETH, Computer Science at ETH Zurich
Github Skills (13)
scikit-learn10
forecasting10
machine-learning10
forecast10
time-series10
python10
scikit10
data-science9
numpy9
pandas8
unit-test8
anomaly-detection8
regression-models7
Programming languages (2)
Github contributions (5)
unit8co/darts
Oct 2021 - Aug 2022
A python library for user-friendly forecasting and anomaly detection on time series.
Role in this project:
Data Scientist
Data ScientistContributions:30 reviews, 100 commits, 19 PRs in 10 months
Contributions summary:Dustin primarily focused on enhancing the darts library, a Python library for time series forecasting and anomaly detection. Their contributions involved fixing issues and improving the regression model for multivariate time series, adding new features like autoregressive time series generation and related unit tests, and optimizing the model fitting process. They also addressed documentation issues, making the library more user-friendly.
forecastingpython-libraryanomalypythontime-series-analysis
brunnedu/brunnedu.github.io
Oct 2024 - Oct 2024
Contributions:51 pushes, 1 branch in 8 days
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.