Services
Upskilling engineers to use modern AI tools effectively — prompt/context engineering, evaluation habits, and workflows that ship.
Designing autonomous agent systems with proper tool use, memory management, and context window optimization.
Building Model Context Protocol servers that give LLMs structured access to your systems and data.
Taking AI from prototype to production with proper error handling, observability, cost management, and reliability.
Building the developer tooling, shared libraries, and infrastructure that make AI adoption frictionless for engineering teams.
Event-driven and microservice architectures in Azure and Kubernetes, backed by 12+ years of production engineering.
Writing
Python fits up to 90% more logic into an LLM context window than C#. 600+ identical algorithms tokenized across 6 languages to measure the hidden cost of verbose syntax.
MIT's RLMs replace soft attention with hard programmatic search — cutting inference costs 40-64% while outperforming traditional LLMs on complex long-context tasks.
About
I spent 12+ years building high-scale systems at LEGO, MobilePay, and Universal Robots — payment platforms, cloud infrastructure, developer tooling. Now I help engineering teams design and build AI systems that survive contact with production.
Context engineering, agent architecture, MCP servers, and the hard problems of getting LLMs to work reliably at scale. Not demos — systems that ship.
