Maarten Grootendorst
Developer Relations Engineer
North Brabant, Netherlands
Summary
🤩
Rockstar🎓
Top SchoolMaarten Grootendorst is a Developer Relations Engineer and AI practitioner with nine years of experience bridging research, open source, and industry adoption of large language models. He authored the Amazon #1 bestseller "Hands‑On Large Language Models," maintains widely used libraries like BERTopic and KeyBERT with over 10 million downloads, and teaches a DeepLearning.AI course watched by 50,000+ students. His background in clinical and organizational psychology, combined with cum laude degrees in data science and psychology, informs a pragmatic focus on usable, ethically minded ML tools—evident in federated LLM work for healthcare at IKNL. A prolific communicator and speaker for companies like NVIDIA and Hugging Face, he also runs a popular newsletter and open-source projects that have become standard tooling for NLP practitioners.
9 years of coding experience
7 years of employment as a software developer
Master of Science - MS Data Science and Entrepreneurship (Cum Laude), Master of Science - MS Data Science and Entrepreneurship (Cum Laude) at Jheronimus Academy of Data ScienceMaster of Science - MS Clinical Psychology (Cum Laude), Master of Science - MS Clinical Psychology (Cum Laude) at Tilburg University
Dutch, English
Stackoverflow
321reputation
8kreached
11answers
0questions
Github Skills (21)
transformers10
keyword-extraction10
python10
imap10
machine-learning10
hdbscan10
topic-models10
omap10
bert10
topic-modeling10
nlp10
pandas9
unit-testing9
pytest9
scikit9
Programming languages (5)
Github contributions (5)
MaartenGr/BERTopic
Sep 2020 - Jan 2023
Leveraging BERT and c-TF-IDF to create easily interpretable topics.
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:30 releases, 110 reviews, 298 commits in 2 years 3 months
Contributions summary:Maarten primarily focused on updating and improving the `bertopic` model, a project leveraging BERT and c-TF-IDF for topic modeling. Their contributions centered on refining the model's core functionality, including document transformation, topic reduction, and the extraction of topics using c-TF-IDF. The user also added functionalities like seed topic list, probabilities and reduced topics. They incorporated improvements to c-TF-IDF processing, and overall, their work was centered on the mathematical and machine learning components within this project.
nlptransformersbertleveragingmachine-learning
MaartenGr/KeyBERT
Oct 2020 - Nov 2022
Minimal keyword extraction with BERT
Role in this project:ML Engineer
ML EngineerContributions:11 releases, 17 reviews, 87 commits in 2 years
Contributions summary:Maarten primarily contributed to the core functionality of the KeyBERT library. The contributions involved implementing maximal marginal relevance (MMR) and max sum similarity algorithms for keyword extraction, enhancing the library's capabilities. Furthermore, the user added unit tests and documentation, demonstrating a focus on software quality and usability. They also added features for a custom vectorizer, seed keywords and embedding methods.
nlpextractionbertword-embeddingskeyphrase-extraction
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.