Systems Engineer · San Francisco
I build the infrastructure behind practical AI.
Local inference, automation, observability, and the systems that turn AI models into something you can actually operate.
Live system metrics
Measured from systems I build and operate.
Selected work
Systems I build and operate.
01
Live Environment
Homelab Infrastructure
Distributed compute fabric for local AI, automation, observability, media workflows, and experimental applications.
Mac Mini M4
Dell Pro Max GB10
Raspberry Pi 5
Raspberry Pi Zero 2 W
02
Active Development
AI Agent Orchestration
Multi-model agent environment for tool use, infrastructure interaction, and workflow execution across local systems.
Qwen
Llama
Gemma
Ollama
03
Active System (v1 Live)
Cronitor
Runtime monitoring system for tracking job execution, failures, and automation health across distributed workflows.
Node.js
launchd / system scheduling
Docker
homelab compute nodes
04
Active System (v1 Live)
Co-Worker
AI-powered sales intelligence system that turns daily signals into account insights, prioritization, and actionable outreach workflows.
React
Node/Express
Docker
Ollama
Operating now
A small production environment, not a mockup.
Recent system signals
STATUS
Waiting for live telemetry
01
Control plane
Mac Mini M4
Runtime
Hermes + orchestration
Role
Automation + routing
Status
Checking…
02
Inference
Dell GB10
Runtime
llama.cpp + vLLM
Role
Local model serving
Status
Checking…
03
Application host
Pi 5
Runtime
Docker Compose
Role
Apps + web surfaces
Status
Checking…
Photography
What I notice when I’m not in a terminal.
About the work
Infrastructure is most interesting when people can actually use it.
My background is in systems engineering and infrastructure. I use this lab to explore the layer between hardware, AI models, automation, and the operator experience around them.