I'm an AI platform architect. Most of the distance between an AI demo and an AI system in production is an architecture problem, and that distance is where I've worked for 14 years: agentic AI platforms, internal developer platforms, and the cloud underneath them, across 180+ AWS accounts and 1,000+ developers.
The results I'd point to first: an autonomous FinOps platform projected to return ~$2.1M a year, and a ~$6M vendor contract replaced with open source infrastructure run in-house.
I'm currently building AgentGuardian, a runtime trust and governance control plane for AI agents. M.S. in Computer Science, Rice University (2026).
Metrics are real. Employer and internal system names are left out, here and in the linked write-ups.
Cloud waste and misconfiguration pile up faster than a small team can review them. I architected a multi-agent platform on Amazon Bedrock that finds them, proposes fixes, applies what a person approves, and returns a week later to score its predictions against actual savings. The model never holds credentials, and nothing irreversible runs without human sign-off.
Security triage was consuming four full-time engineers. I architected the platform (Bedrock, AgentCore, LangGraph) that automated most of it, with the same rule as everything I ship: the model proposes, deterministic code validates, a person authorizes.
Public write-up in progress.
We replaced a commercial cluster-management product with a CNCF open source stack and migrated 145 production EKS clusters to it in four months, with zero rollbacks. Fleet-wide upgrades went from weeks of manual effort to a single Git commit.
I'm open to conversations about enterprise AI platforms and Staff, Principal, or Distinguished architect roles. Reach me on LinkedIn.