Senior Software Engineer · London, UK
Building AI-native products that ship
I write about LLMs, voice AI, full-stack TypeScript, and the craft of building production-grade AI systems. Practical deep dives, no fluff.
Latest Posts
View all
AIReactPerformance
Why Your LLM App Feels Slow (And It's Not the Model)
An LLM generating 50 tokens/second isn't slow — but if your UI makes the user stare at a spinner for the first 2 seconds, it feels slow. Most LLM latency is a UX problem, not an infrastructure problem.
April 5, 20266 min read
AIHIPAASecurity
Building HIPAA-Compliant AI Features: What the Tutorials Skip
Integrating AI into a healthcare product isn't just about plugging in an API. HIPAA has specific requirements around PHI, audit logging, and vendor agreements that most AI tutorials completely ignore.
March 28, 20266 min read
AILLMsPython
The Hidden Cost of Context Windows: Managing Tokens in Production
128k tokens sounds like infinite space until you're paying $0.40 per conversation and users are hitting limits mid-session. Here's how I actually manage context in long-running AI applications.
March 18, 20265 min read