Hannah Marie Tosi
I am a Senior Software Engineer with Red Hat, and I primarily develop ML-focused JupyterLab extensions. I have a background in mathematics and statistics, and I previously worked as a cancer informatics data scientist. I am based in Boston in the United States, and in my free time, I enjoy running, skiing, and biking with the people I love.
Red Hat
Senior Software Engineer
Session
We contribute to open source JupyterLab extensions (Kale, Elyra) that transform notebooks into production ML pipelines. This talk explores our technical platform and our path to programming integrated AI architecture within our developer tools.
Our community’s TypeScript/React frontends and Python backends map data flows into Directed Acyclic Graphs (DAGs), extracting metadata and compiling user code into pipeline server manifests. The architecture streamlines the transition from experimentation to orchestration and is ideal for supporting integrated AI tools.
The talk will include a demo of Notebook-to-Pipeline conversion, plus our AI roadmap — AI-assisted coding with Kubeflow APIs, LLM-based pipeline optimization, and an integrated genAI development environment.
This session is ideal for IDE developers, MLOps engineers, and data scientists, or anyone who wants to learn about building and utilizing LLM-ready JupyterLab extension architectures.