I spent four decades designing the systems that move the world's data — carrier networks,
enterprise architecture, telecom infrastructure at scale. Then AI happened, and I pivoted
completely. Not as a passenger. As a builder.
My edge: I don't just use AI tools — I architect the infrastructure
underneath them. Memory systems. Persistent agent identity. Cloud-native AI deployments
that survive crashes, resets, and disasters. I call it Survivability as a Service.
The latest chapter: enterprise LLM cost optimization. I run a production multi-model
gateway — LiteLLM proxying 15+ providers — with prompt caching on Claude, GPT-4o, and
Gemini that cuts inference costs 60–70% on long sessions. The same
infrastructure discipline that built carrier networks, applied to AI cost at scale.
Based in Deep East Texas. My personal engineering projects now span healthcare AI,
fintech, and cloud infrastructure — built nights and weekends alongside a 35-year
carrier career. Available for senior AI engineering contracts at $150–200/hr.
AI Infrastructure
LLM Engineering
LLM Cost Optimization
LiteLLM / Model Gateway
Agentic Systems
Carrier Networks
Cloud Architecture
MCP / RAG
Node.js / Python
GCP / K8s
