Tag: experience
-
Deploying self-hosted LLMs in Prod
A practical walkthrough of deploying a self-hosted LLM on AWS EKS with dedicated GPU node groups, taints/tolerations for isolation, separate inference and app services, model-weight caching via volumes, and sizing guidance for VRAM/concurrency and warm GPU capacity.
-
Mobile App Agentic Patterns
I’ve been building mobile apps that leverage LLMs for almost four years, and the hardest lessons didn’t come from prompts—they came from the phone itself. Mobile copilots feel inevitable: we already live in our messaging apps, and text is the most natural UI we have. But building copilots on a device that’s both highly privileged…
-
Building and Securing Publicly Facing AI Agents
A CV is compressed text. It is easy to skim, easy to misread, and hard to validate. So instead of publishing my background as static pages, I built a public, live AI agent on top of my Notion database. The goal is simple: don’t just read my CV. Interact with it. Ask questions in your…
Juan Alberto López Cavallotti 