Tom Aarsen
Machine Learning Engineer at Hugging Face
Tiel, Gelderland, Netherlands
Summary
🤩
Rockstar🎓
Top SchoolTom Aarsen is a Machine Learning Engineer and Hugging Face Fellow with eight years of experience specializing in NLP and open-source tooling. He maintains key projects like Sentence Transformers, SetFit and contributes to NLTK, Transformers, and bitsandbytes—work that spans few-shot learning, tokenization edge cases, and k-bit quantization stability. At Hugging Face he combines hands‑on engineering with documentation and CI improvements to make state‑of‑the‑art models and libraries more robust and accessible. His background includes applied ML roles building NLG systems for product descriptions and improving algorithmic components like TopicRank in pytextrank. Based in the Netherlands, he pairs a Radboud University computer science education with a practical focus on reliability, performance, and developer experience across popular ML repos.
7 years of coding experience
1 year of employment as a software developer
Master of Science - MS Computer Science, Master of Science - MS Computer Science at Radboud University
English, Dutch
Stackoverflow
1,180reputation
25kreached
53answers
0questions
Github Skills (36)
tokenize10
pytorch10
language-model10
sentence-transformers10
python10
pre-trained-model10
testing10
machine-learning10
deeplearning-ai10
textrank10
tokenizer10
deep-learning10
spacy10
natural-language-processing10
text-processing10
Programming languages (14)
Github contributions (5)
nltk/nltk
Aug 2020 - Jan 2023
NLTK Source
Role in this project:
Back-end Developer & Technical Writer
Back-end Developer & Technical WriterContributions:133 reviews, 188 commits, 126 PRs in 2 years 4 months
Contributions summary:Tom primarily contributed to the Natural Language Toolkit (NLTK) repository by addressing bugs, adding tests, and improving documentation. Their work involved fixing issues related to tokenization, including dealing with edge cases in the `PunktSentenceTokenizer` and `TreebankWordTokenizer`. They also refactored code and added a function for the correct processing and rendering of files. These efforts indicate a focus on improving the robustness, documentation, and maintainability of the library.
nlppythonmachine-learningnltknatural-language-processing
huggingface/setfit
Nov 2022 - Jan 2023
Efficient few-shot learning with Sentence Transformers
Role in this project:ML Engineer
ML EngineerContributions:4 releases, 99 reviews, 15 commits in 2 months
Contributions summary:Tom primarily contributed to improving the functionality and stability of the `setfit` library, which is designed for few-shot learning with Sentence Transformers. Their contributions include fixing typos, enhancing error handling for the training process, and adding the ability to disable progress bars during training. The user also addressed class imbalance warnings and refactored code to optimize model state handling. Furthermore, the user expanded CI tests.
nlppytorchsentencetransformerslanguage-model
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.