Systems Engineer
for Practical AI

Real infrastructure, local AI systems, and automation built for day-to-day use.

Based in San Francisco, CA
Background Texas roots · Austin educated · NYC → Madrid → Boston → SF

Live System Dashboard

Real-time execution metrics from local AI infrastructure.

Estimated Cost Savings
--
API spend avoided through local inference
LLM Calls Executed
--
Total local inference requests
Throughput
--
Tokens per second
Engineering Time Saved
--
Hours returned to productivity

Recent System Signals

Mac Mini M4 Control Plane
Runtime Ollama / Hermes
Role Scheduler + Workflows
Status Active
Dell GB10 Inference Host
Runtime llama.cpp + Ollama
GPU NVIDIA GB10
Status Active
Pi 5 App Server
Runtime Docker Compose
Surface Portfolio + APIs
Status Active

Selected Works

Product case studies with measurable infrastructure impact.

Photography

Street photography, travel frames, and everyday moments.

Interested in the projects, systems, or background behind all this?

Always happy to talk infrastructure, AI systems, automation, photography, or new opportunities.

Get In Touch