Profile and capabilities
I help teams build and operate AI infrastructure: GPU clusters, Kubernetes, GitOps delivery, and the monitoring and recovery procedures needed to support them.
Explore the work
- Dashboards, runbooks, and reproducible baselines: readiness audit.
- Read the systems behind this site: factory, inference plane, and cluster.
- Notes on constraints, verification, and what changed: case studies.
Capabilities
What I do
The work is usually a mix of platform engineering and operational design. I focus on the places where teams lose time: unclear bottlenecks, risky deploys, and dashboards that don't match the on-call questions.
- GPU platforms: scheduling, routing, scaling, and ongoing operations
- Cost analysis: throughput, spend, caching, batching, and routing
- GitOps reliability: safer rollouts, environments, rollbacks
- Observability: signals, alerts, and runbooks tied to ownership
What you get
I try to ship artifacts you can reuse after I'm gone: baselines, docs, dashboards, and an execution plan that fits your constraints.
- Baseline report: workload profile + bottlenecks + cost curve
- Deployment model: topology, capacity, and scaling strategy
- Dashboards + alert thresholds (first pass)
- Runbooks: alerts -> actions
- 90-day plan: owners, milestones, and risk register
Typical engagement
Agree on the workload, instrument the right signals, and produce a cost/latency baseline you can reproduce.
Put guardrails in place: routing, budgets, autoscaling, and rollout/rollback with clear abort conditions.
Build dashboards and alerts for on-call questions. Document response steps, owners, and remaining work.
Compare each change against the baseline and use the results to choose the next improvement.
Proof
Live systems
Factory runs, loaded models, and cluster health, each panel labelled live or snapshot.
Case Studies
Implementation write-ups covering constraints, changes, verification, and limitations.
Projects
Open-source and internal tools supporting GitOps, AI infra, and visualization work.
Background
My background is in healthcare integration, API support, and technical delivery. That experience shapes how I approach infrastructure and ongoing operations.
Let's talk
Tell me what you're building, where it's getting stuck, and what you've tried. We can use that context to decide on a useful next step.