Tag: nlp

• 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.

  juancavallotti

  March 30, 2026

  Machine Learning, Software Engineering, Technology

  ai, artificial-intelligence, chatgpt, experience, llm, Machine Learning, nlp, personal growth, Software Engineering, Technology

• Reference Architecture: An Agentic CLI Application

  

  While writing the previous post in this series, I hit a very unglamorous problem: my laptop disk was full. Not “almost full”. Full enough that everything started to feel brittle. I did what I always do: open a couple of folders, run a few du commands, check caches, look for the usual suspects, delete stuff,…

  juancavallotti

  March 2, 2026

  Machine Learning, Software Engineering, Technology

  ai, artificial-intelligence, chatgpt, cli, github, llm, Machine Learning, nlp, open source, reference architecture, Software Engineering, Technology

• 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…

  juancavallotti

  February 27, 2026

  Machine Learning, Software Engineering, Technology

  agentic architecture, agents, ai, architecture, artificial-intelligence, experience, language processing, llm, nlp, personal growth, reference architecture, Software Engineering, Technology