I build and ship AI products. Chief Technology Officer at Tellme AI, founder of EchonLabs (exited), and author of From Model to Product. 15+ years turning engineering, AI research, and entrepreneurial bets into shipped, scalable products.
Having built and scaled EchonLabs from the ground up to a team of 80+, now positioned for acquisition, I've learned that the most impactful work happens at the boundary between deep technical expertise and real-world business problems.
My journey spans software architecture, machine learning research, and digital transformation, enabling me to drive scalable solutions across industries - from healthcare AI at Queen's University Belfast to agentic AI experiences deployed in real-world environments like museums and public spaces.
I believe that production is where ideas become real. Not in notebooks. Not in demos. In systems that handle real users, edge cases, and the unpredictable messiness of the world.
Bringing AI-driven solutions to industries - from production-ready ML systems and LLM architectures to edge AI and intelligent automation that creates real business impact.
From founding EchonLabs to building a team of 80+ and positioning it for acquisition - I specialise in driving product strategy, building high-performing engineering cultures, and navigating the chaos of growth.
My research bridges academia and industry - from healthcare AI and predictive modelling to NLP, computer vision, and retrieval-augmented generation for production systems.
Most AI content stops at models. Real systems don't. This book is about everything that comes after - architecture, pipelines, deployment, and making AI work in production for real users.
Recognised for pioneering agentic AI systems at Tellme AI
National recognition for outstanding achievement in ICT
Komposer project — Gold Award in the Tertiary category at the Asia-Pacific ICT Alliance Awards.
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.
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.
Building real-time computer vision on low-end mobile devices comes with unique challenges - especially when every second of inference drains battery. Here's how I optimised similarity search using HNSW and hybrid re-ranking to cut battery usage by over 50%.
“As CEO of Tellme, I work very closely with Dulan in his role as Chief Technology Officer. He has taken full ownership of our technical direction - designing and building core architecture across computer vision, AI systems, and the full product experience. What impresses me most is his ability to operate across the full stack while maintaining strong product focus, making pragmatic decisions that balance speed, quality, and scalability. His contribution has been central to our progress, including rolling out the product and securing funding. He's a genuinely exceptional technical leader.”
A curated collection of thoughts, ideas, and innovations at the intersection of AI, technology, and engineering. No spam — only things worth your time.
By subscribing you consent to receiving email communications. Unsubscribe anytime. Privacy Policy
