About
Engineering foundation, AI direction.
I build AI applications, agents and automated systems with the mindset of an engineer experienced in production workflows.
My earlier work focused on infrastructure automation, monitoring, Python tooling and systems integration. That background now shapes how I approach AI: define what the model should decide, what code should control, what data is needed and what action follows.
How I think about AI
What happens after the answer?
The useful part of an AI system often starts after generation: research, structured decisions, data lookup, automation, escalation, storage and follow-up. I design around that full path rather than treating the model as the product.
Working stack
Tools are secondary to the system.
This is a curated view, not a wall of logos.
AI & product
LLMs, prompt and workflow design, AI feature design, local model experiments, evaluation-minded product thinking
Automation & integration
Python, n8n, APIs, Shopify integrations, operational workflows, notifications and escalation
Engineering foundation
Infrastructure automation, monitoring, NetBox, Nagios, ServiceNow-style operational processes, systems integration
Current learning
AI engineering, agentic systems, cloud architecture and deployment
Engineering evidence
Production experience before the AI portfolio.
Previous automation work included production monitoring, infrastructure reconciliation, operational notifications and repeatable systems workflows. Public portfolio material intentionally removes employer names, internal code and confidential details.
Next
See the projects where that foundation becomes AI product work.
Built across AI product development, automation, APIs, local LLMs and production workflows.