Design.
Problem
What actually needs solving, and what does not.
Architecture
The shape of the system, decided before anything is written.
Infrastructure
Servers, network and storage sized to the real workload.
✳
I turn ‘what if’
into what’s next.
into what’s next.
I design, build and run AI infrastructure, real-time platforms and automation—from first sketch to production.
Ideas, put to work.
All case studiesFrom first sketch
to production.
Most technical work stalls between the whiteboard and the server. I stay responsible for the whole line.
Inside my approachBuild.
Backend
Services, APIs and the data model underneath them.
Interface
Dashboards and controls someone else can operate safely.
AI integration
Models wired in only where they earn their place.
Operate.
Automation
Repetitive work removed, with verification built in.
Monitoring
Health, alerting and honest failure states.
Production
Live, owned, and still my responsibility afterwards.
The tools behind
the thinking.
Full capability matrix Languages
Python · TypeScript · JavaScript · Bash
Frontend
React · Responsive interfaces · Dashboards · Real-time UI
Backend
FastAPI · Node.js · REST APIs · WebSockets
AI & ML tooling
Local LLM deployment · GGUF · Quantization · Agent architecture
Automation
Playwright · Browser automation · Workflow orchestration · Event-driven processes
Infrastructure
Linux · Docker · Nginx · GPU servers
Built with intention.
What guides the workOwn it end to end.
Architecture, infrastructure, code, deployment and the pager afterwards. Systems fail at the seams between people.
Verify, do not assume.
Automation reports what it thinks it did. Independently checking the resulting state is what makes it trustworthy.
Make it operable.
Infrastructure only one person can run is a liability. The goal is an interface someone else can use safely.