Gonzalo Andrés Peña Castellanos

About

I'm a Colombian software engineer with 11+ years of professional experience, and entrepreneur working in Python, TypeScript and open source development. I currently work as an AI Engineer at Backblaze. Previously, I worked at Datalayer building tools at the intersection of Jupyter, AI, and collaborative computing, at Quansight contributing to the scientific Python ecosystem, and at Anaconda as Technical Lead for Anaconda Navigator. My career spans from water resources engineering (MSc from IHE Delft and Erasmus Mundus) to becoming a core contributor to major open source projects including Spyder IDE, JupyterLab, and napari, conda-forge among others. I've created over 400+ conda-forge recipes and led internationalization efforts for JupyterLab and automating efforts in the Scientific Python Translations project. I also co-founded Trepa, a climbing gym in Bogotá, Colombia, and co-founded PyCon Colombia. I'm deeply committed to the Latin American Python and open source communities, and serve on the Python Software Foundation Grants Working Group.

Talk

Provenance by Default: AI Media Pipelines in Python

A model can now generate a video that looks indistinguishable from one your camera recorded. The same is true for an image, a voice, or a song. As Python developers, we are building those pipelines — and we are also the ones who will be asked, very soon, to prove what came out of them. This talk is about building generative media pipelines in Python in a way that answers that question by default. We'll walk through Genblaze, an open-source SDK (github.com/backblaze-labs/genblaze, MIT licensed) that I work on at Backblaze, and use it as a vehicle to talk about the design problems any team faces when wiring AI generation into a real product. We will cover, with live code: the Pipeline pattern with a fluent Pipeline → Step → Run → Manifest API built on Pydantic v2; one API across eleven providers; provenance that survives the file with SHA-256-verified manifests embedded into PNG, JPEG, MP4, MP3, and WAV; privacy and policy controls; storage and replay; and agent loops with lineage. By the end, attendees will have a clear reference for how to architect generative-AI features in Python so that what did this system actually produce, and can I prove it? is a one-line answer instead of a ticket.

Country

Colombia

Language

Spanish / Español

Level

Intermediate / Intermedio