Valentin Flunkert
Principal Applied Scientist at Amazon Web Services (AWS)
Berlin, Germany
Summary
🤩
Rockstar🎓
Top SchoolValentin Flunkert is a Principal Applied Scientist based in Berlin with nine years of industry experience building production-ready ML and time-series systems at Amazon and AWS. He holds a doctoral background in physics from TU Berlin and progressed from software development into machine learning roles, blending rigorous research instincts with pragmatic engineering. At AWS he has driven applied-science projects and contributed to open-source probabilistic time-series tooling—making substantive gluonts improvements such as respecting evaluation sampling parameters and adding distribution CDF support. Known for clear API and documentation work as well as core algorithmic fixes, he excels at turning complex probabilistic models into usable, well-documented components for practitioners.
9 years of coding experience
11 years of employment as a software developer
KTH Royal Institute of TechnologyDr. rer. nat. Physics, Dr. rer. nat. Physics at Technische Universität Berlin
English, German
Github Skills (12)
forecasting10
machine-learning10
forecast10
deep-learning10
time-series-forecasting10
python10
data-science10
numpy10
documentation9
mxnet9
testing8
api-design8
Programming languages (5)
Github contributions (5)
awslabs/gluonts
May 2019 - Dec 2020
Probabilistic time series modeling in Python
Role in this project:
Data Scientist / ML Engineer
Data Scientist / ML EngineerContributions:63 reviews, 39 commits, 81 PRs in 1 year 6 months
Contributions summary:Valentin's commits primarily focus on improving the documentation and functionality of the `gluonts` library, a Python-based time series modeling framework. They updated API documentation for the `time_feature` subpackage, including file modifications in `lag.py`, `_base.py`, `holiday.py`, and `__init__.py`, improving the readability and usability of the library. Further contributions involve updating documentation related to the `transforms.py` module, enhancing the clarity of the API. The user also made significant improvements to the core functionality with commits like respecting the num_eval_samples parameter and including the cdf method in the distribution, indicating deep understanding of the project's core.
forecastingpythontime-series-analysistimeseries-forecastingaws
vafl/gluon-ts
Jun 2019 - Nov 2021
GluonTS - Probabilistic Time Series Modeling in Python
Contributions:1 PR, 104 pushes, 69 branches in 2 years 5 months
forecastingpythontime-series-analysismachine-learningprobabilistic
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.