Principal engineer with 14 years across infrastructure, DevOps, and platform architecture, now leading applied AI at enterprise scale: local LLM inference (vLLM), agentic and MCP-based systems, governed RAG, and AI cost optimization. Sets direction for model selection, evaluation, and responsible AI consumption while staying hands-on; track record of architecting provider-agnostic platforms and multiplying the teams around them.
Experience
Beaverton, OR
- Set enterprise direction for applied AI practices: model selection, retrieval strategy, evaluation and experimentation, MLOps, and responsible AI and model governance for production use.
- Architected a schema-as-guardrails platform that lets citizen developers generate code to company specification safely, enforcing secure tool and data access through approved containers, platforms, and reusable patterns rather than one-off solutions.
- Designed MCP-based developer tooling (a symbol-index server) that reduced code analysis costs by ~70% by feeding models precise, governed context instead of bulk source.
- Maintained and operated internally-hosted LLM inference infrastructure (vLLM) at enterprise scale, serving internal chat and code-generation workloads.
- Built the framework for enterprise Microsoft Copilot adoption, including Copilot Cowork and Copilot Studio.
- Multiplied teams through architecture reviews, reusable patterns, and mentorship across engineering organizations.
Beaverton, OR
- Led the Release Engineering Core team (6 developers, systems engineers, and architects) and its Agile process; owned the global retail release platform.
- Spearheaded quality efforts for high-demand ("high-heat") sneaker releases; founded an internal engineer training initiative to grow team capability.
Beaverton, OR
- Architected a containerized, cloud-provider-agnostic global release management platform (Azure, AWS, and datacenter deployments) and handed it off cleanly to the owning team.
- Designed a global package distribution system that cut deployment time from 9 days to 1 hour, removing an infrastructure bottleneck and raising release velocity.
Beaverton, OR
- Designed a global retail testing methodology (Ansible + Nutanix) that reduced lab creation from 1 week to 1 hour and release testing from two weeks to under one business day.
- Used infrastructure-as-code to guarantee test-environment integrity; helped other teams automate daily work with Ansible and Python.
Beaverton, OR
- Built company-wide CA Service Virtualization training and processes, eliminating ~$1M/month in infrastructure spend.
Salem, OR
- Maintained the company datacenter (Nutanix Acropolis, Meraki networking, Nagios) and mentored junior administrators and developers.
Albany, OR
- Supported 2,000+ end users across 5 remote sites; built and deployed systems; mentored technicians and interns.
Jacksonville, NC
- Accountable for $19M in weaponry and electronics; developed and delivered training to 40,000+ Marines; mentored 15 junior Marines into leadership roles.
Open Source & Projects
Synaptic Drift: governed context retrieval for LLM agents
status: open source · in active development
- Retrieval-augmented generation (RAG) system serving verifiable, governed context to agents over MCP with schema-enforced tool contracts; ~80% token reduction on documentation/context retrieval in testing to date.
- Validated by end-to-end task success: building working functionality against live, unseen library docs using a 9B model, so retrieval quality couldn't be masked by model capability. Sub-21ms P95; cryptographic content verification and lifecycle governance.
Vamp: schema-as-guardrails platform for citizen developers
status: personal · in active development
- Lets citizen developers write and ship code to company specification safely, enforcing secure tool and data access through schema-defined guardrails instead of manual review.
Education & Honors
- B.A. Thomas Edison State University (2024)
- A.S. University of South Carolina (2006–2008)
- Navy and Marine Corps Achievement Medal
Key Engineering Highlights
- Cost Reduction: Designed MCP-based developer tooling that cut code analysis costs ~70% by feeding models precise, governed context instead of bulk source.
- Safety & Scale: Architected a schema-as-guardrails platform that lets citizen developers generate code safely to company specification, enforcing secure tool and data access through approved containers and reusable patterns instead of one-off solutions.