About
Backend engineering, increasingly applied to AI systems
I’m a senior software engineer with a background in backend and distributed systems and an increasing focus on applied AI engineering.
My current interests sit around the boundary between probabilistic models and ordinary software engineering: how to make LLM-enabled systems observable, testable, reproducible, and simple enough to operate without hiding important behaviour behind a framework.
That includes AI-assisted software engineering, LLM evaluation, agent architectures, developer tooling, software architecture, model and harness routing, context engineering, and reliable automation. I’m especially interested in mechanisms that preserve useful human judgement while moving repeatable work into deterministic code.
I use projects and small experiments to work through those questions. The aim is usually not to invent a new platform; it is to find the smallest mechanism that makes a real workflow more dependable.
Professional focus
- Backend and distributed software systems
- AI-enabled applications and agentic workflows
- LLM evaluation and reliability
- Developer tooling and repository intelligence
- Software architecture and dependable automation