Bryan Ramos

Bryan Ramos

Linux Systems & Automation Engineer

I work on Linux systems, real-time computing, automation, and applied AI tooling. My work spans low-level diagnostics, C/C++ and Python development, reproducible infrastructure, and debugging latency-sensitive systems where correctness and determinism are critical.

Lately I have been focused on learning Rust, minimizing vendor dependencies for developer workflows and automation via RAG AI pipelines.

Reach me at bryan@ramos.codes

Stack & Tools

Linux Real-Time Systems Diagnostics Automation Git APIs Service Integrations Nix/NixOS C/C++ Python Bash Docker SQL Networking KVM/QEMU AI/LLM Integration RAG MCP

Recent Posts

April 16, 2026 Experimenting With TurboQuant and MoE Caching

Some notes from maintaining a TurboQuant llama.cpp fork and testing whether hot MoE experts on the GPU could make a huge local model practical.

March 18, 2026 Building a Local AI Rig

The machine I built for local AI work, why I built it, and why good enough hardware changes how I use these tools.

February 10, 2026 Why I'm Moving More AI Work Off the Cloud

Cloud AI is useful, but I want more of my day-to-day AI workflow on infrastructure I control.

View all posts →