🤓 Jules Belveze ┣━━ 📦 Open Source ┃ ┣━━ tsa - Dual-attention autoencoder ┃ ┣━━ bert-squeeze - Speed up Transformer models ┃ ┣━━ bundler - Learn from your data ┃ ┣━━ nhelper - Behavioral testing ┃ ┗━━ time-series-dataset - Dataset utilities ┣━━ 👍 Contributions ┃ ┣━━ 🤗 Hugging Face Ecosystem ┃ ┃ ┣━━ t5-small-headline-generation - t5 for headline generation ┃ ┃ ┗━━ tldr_news - Summarization dataset ┃ ┣━━ ❄️ John Snow Labs Ecosystem ┃ ┃ ┗━━ langtest - Deliver safe & effective NLP models ┃ ┣━━ 🧹 Dust ┃ ┃ ┗━━ Dust - Customizable and secure AI assistants. ┃ ┣━━ 💫 SpaCy Ecosystem ┃ ┃ ┗━━ concepCy - SpaCy wrapper for ConceptNet ┃ ┣━━ bulk - contributed the color feature ┃ ┗━━ FastBERT - contributed the batching inference ┗━━ 📄 Blogs & Papers ┣━━ Atlastic Reputation AI: Four Years of Advancing and Applying a SOTA NLP Classifier ┣━━ Real-World MLOps Examples: Model Development in Hypefactors ┣━━ LangTest: Unveiling & Fixing Biases with End-to-End NLP Pipelines ┣━━ Case Study: MLOps for NLP-powered Media Intelligence using Metaflow ┣━━ Scaling Machine Learning Experiments With neptune.ai and Kubernetes ┗━━ Scaling-up PyTorch inference: Serving billions of daily NLP inferences with ONNX Runtime
I currently work as a Core Team Researcher @H Company, building computer use agents. Previously spent 2+ years building AI Agents and community @Dust, with prior experience in MLOps, NLP, and deep learning research at Ava, John Snow Labs, Hypfactors, and Microsoft. Passionate about automating model development and deployment, open source, and ethical AI practices.
Series. Additionally, I am keenly interested in exploring state-of-the-art techniques to speed up the inference of Deep Learning models, especially Transformer-based models.
I am an avid open source contributor and advocate for ethical AI practices.