Experience

  • From Model to Product: Foundations for Practical AI Engineering

    , ,

    Everyone is building with AI today. Very few are building systems that actually work in production. This article explores the real gap between models and products, and why thinking like an AI engineer matters more than ever.

  • Building a Production-Ready Prompt Engine: How I Designed a System That Handles Everything from Dynamic Templates to Multi-Layer Guardrails

    , ,

    A behind-the-scenes look at how I designed and built a production-ready prompt engine—from dynamic templates and reusable components to multi-layer guardrails, structured output, and parallel execution. This architecture powers real-world AI assistants, agents, and workflow systems.

  • Bringing Computer Vision to the Edge: How I Cut Real-Time Similarity Search Battery Usage by 50%

    , ,

    Building real-time computer vision on low-end mobile devices comes with unique challenges—especially when every second of inference drains battery. In this deep dive, I share how I optimized similarity search using HNSW, hybrid re-ranking, and edge-focused techniques to cut battery usage by over 50% while keeping accuracy nearly perfect.

  • NI Tech Awards 2025: Belfast’s Tech Ecosystem Has Its Moment

    ,

    The inaugural NI Tech Awards 2025 lit up Belfast with energy, community, and recognition for Northern Ireland’s brightest tech talent. For me, it was the first time experiencing this ecosystem’s brilliance — and it reminded me of the award nights I once attended (and even won at) back in Sri Lanka, years ago.

  • Why I Chose Preact (And Why I Might Never Look Back)

    ,

    When performance is non-negotiable and the app must shine on low-end devices, you start questioning your default stack. Here’s why I chose Preact — the tiny, powerful alternative to React — and how it reshaped my dev experience on the edge.