Systems & Infrastructure · Applied AI
I build and run systems // from the network up
scroll ↓
I build and run the whole stack: hardware, network, identity and access, virtualization, and the AI workloads on top. The projects here are grouped by what each one demonstrates, so you can go straight to the evidence for a given skill.
// featured work
32B QLoRA on 24 GB
Fine-tuned a 32B model on a single consumer Radeon under Windows ROCm, no published recipe at this size.
training · ROCm →
AMD GPU wedge, investigated
A silent compute stall every Windows health check called normal. Narrowed to the MES firmware scheduler and filed upstream.
debugging · drivers →
Home AI orchestrator
One local door to the whole fleet: per-user RAG, citations through tools, capability-matched scheduling, nine safety invariants.
RAG · agents · scheduling →
Self-engineering loop
The AI proposes changes to its own orchestrator; every change clears a 2,424-test gate and a human promotion.
agents · CI/CD →
Nursing & law pilots
Two real-user pilots on the orchestrator: hybrid retrieval, clinical-safety checks, defects fixed through use.
RAG · real users →
Operating doctrine
The rulebook for the agents in my lab: twenty-one failure classes, each anchored to a real incident, enforced in tooling.
practices · governance →
The Gauntlet
Over 1,000 model-by-device runs across the ARM cluster, producing verified worker tiers for local routing.
evaluation · benchmarking →
Distributed ARM compute
Eleven low-power nodes, seventy-six cores, for independent-task parallelism and model-scale evaluation.
distributed · fleet →
Cross-scale adapter transfer
A controlled negative result: can a 32B model's adapter cross scales onto its 4B sibling by linear algebra alone?
experiment · eval →
// more work