Hi, I'm Jose Baez — Sr. Cloud Support Engineer
IT professional with 13+ years in financial and government environments — cloud computing, infrastructure, systems administration, networking, and a healthy obsession with understanding how things work under the hood.
Right now I'm focused on applying AI to real infrastructure problems, getting deeper into automation, fine tuning, high performance, and building useful tools for my work and the community. When I step away from the terminal, I'm usually on a hiking trail, a ski slope, or taking something apart just to see if I can put it back together — no leftover pieces, I promise.
Based in New York City.
Projects
GuardRailScan
Automated red-teaming and remediation tool for LLMs, RAG pipelines, and AI agents. Fires adversarial probes, scores every response with a judge LLM, classifies risk severity, and produces a step-by-step audit report.
View Project
URL Shortener with Real-Time Analytics
A production-grade Bitly-style URL shortener built on Kubernetes (AWS EKS) with real-time click analytics — geo data, referrer sources, and device breakdown updated via async background processing.
View Project
AI Slack Bot Agent
A serverless AI agent on AWS that receives natural language questions via Slack, reasons using AWS Bedrock (Claude Haiku), calls real AWS tools — DynamoDB, S3, web search — and posts structured answers back to the channel.
View Project
Writing
Fine-Tuning a Private LLM on AWS — Task-Specific, Secure, and Cost-Effective
A practical guide to tuning an open-weight LLM for a specific business task on AWS — covering data preparation, LoRA/PEFT fine-tuning with SageMaker Spot instances, security hardening with KMS and VPC, and keeping the entire pipeline under $10.
Read Post
AI Guardrails Security — Misconfigurations, Attacks, and Defenses
A deep-dive into the guardrail architectures of Claude, ChatGPT, Gemini, and Llama — covering the most common misconfigurations with fixes, real-world attack vectors, and a practical defense-in-depth checklist for production LLM deployments.
Read Post