Thilo Von Neumann
Research Scientist at Deepgram
Stromberg, North Rhine-Westphalia, Germany
Summary
🤩
Rockstar🎓
Top SchoolThilo Von Neumann is a research scientist with a decade of experience focused on speech technologies and reproducible ML tooling, currently working at Deepgram while pursuing a PhD at Universität Paderborn. He has hands-on research and internship experience in speech separation, recognition, and diarization from NTT Communication Science Labs and contributes to open-source experiment management—enhancing IDSIA/sacred with new commands, core ingredient improvements, and documentation. Comfortable straddling research and engineering, he improves core infrastructure and usability rather than only surface features. Based in Stromberg, Germany, he combines academic rigor from a Computer Engineering MS with practical system-building skills, consistently delivering reproducible, well-documented solutions.
10 years of coding experience
Master of Science - MS Computer Engineering, Master of Science - MS Computer Engineering at Paderborn University
Github Skills (13)
reproducible-research10
rep10
machine-learning10
infrastructure10
reproducible-science10
repr10
python10
cli9
command-line9
command-line-interface9
documentation8
mongodb7
mongodb-database7
Programming languages (5)
Github contributions (5)
IDSIA/sacred
Jun 2018 - Jan 2023
Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:7 releases, 41 reviews, 55 commits in 4 years 8 months
Contributions summary:Thilo primarily contributed to improving the Sacred library's functionality by adding new commands and features. They implemented a command to print named configurations, enhancing the tool's usability. Additionally, the user made significant changes to the internal workings of the ingredient class, adding generic gathering functions, and improving exception handling, suggesting a focus on improving the core infrastructure of the experiment management tool. The user also added detailed documentation for the new command.
pythonorganizeinfrastructuremachine-learningsacred
fgnt/meeteval
Oct 2022 - Mar 2023
MeetEval - A meeting transcription evaluation toolkit
Contributions:168 reviews, 43 commits, 124 PRs in 5 months
asrderwer
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.