~ stockholm, sweden · lead ai architect · 20 years shipping software
I'm Martin McCarthy — Lead AI Architect at Telenor and founder of a production multi-agent SaaS platform. I design the systems, guardrails, and practices that bring agentic AI into the software development lifecycle: safely, measurably, and at enterprise scale.
I'm an Irish software engineer based in Stockholm. My career started in payment systems in Dublin, then ran through lead engineering roles across Swedish fintech, healthtech, and logistics — Qliro, Budbee, Doktor.se — before I founded my own company to build products end to end. I trained in deep learning back in 2017, when it was still a niche pursuit; today AI is the centre of everything I do.
Now I work at the intersection most organisations struggle with: making AI genuinely useful in how software gets built. At Telenor I lead AI architecture for the software development lifecycle — agentic development workflows, the knowledge systems that make large codebases consumable for AI, and the governance that keeps humans approving every stage.
On my own time I practise what I preach: I designed, built, and operate a multi-tenant SaaS platform running three AI agents in production for real businesses — reception, accounts, and marketing — on Google Cloud with Gemini, retrieval-augmented generation, and MCP tooling.
That combination is my edge. I can stand in front of an executive team and argue the strategy, and then open a terminal and ship the system. I don't just advise on AI — I build it, run it, and answer for it in production.
Driving the AI technologies that are reshaping how one of the Nordics' largest telcos builds software. I lead the architecture for agentic development workflows: AI knowledge systems that make large codebases consumable for models, multi-agent delivery pipelines spanning architecture to release, and the governance layer that keeps a human approving every stage. My remit runs from strategy and platform architecture to tool evaluation and hands-on delivery across the engineering organisation.
My own company — senior consulting in web and platform engineering, and the vehicle for building AI products end to end. Flagship: a multi-tenant practice-management SaaS running three AI agents in production — reception, accounts, and marketing — on Google Cloud, with Gemini function calling, RAG over domain knowledge, and MCP tool integration. Designed, shipped, and operated hands-on: architecture, data model, agents, guardrails, CI/CD, and the business itself.
Led frontend development and the agile process at one of Sweden's largest digital healthcare providers, building real-time patient-facing care flows.
Led frontend development at the logistics scale-up, building the real-time systems behind last-mile delivery.
Led a team of six engineers building online payments and checkout for one of the Nordics' largest e-commerce groups.
Opinions and working notes from building agentic systems and rolling AI out across engineering organisations.
Agents will draft every stage of delivery. The organisations that win won't be the ones with the most autonomy — they'll be the ones with the best gates.
read →Developers in a rigorous study felt 20% faster and measured 19% slower. How to evaluate AI tooling with evidence instead of vibes.
read →AI doesn't fix an engineering organisation — it multiplies whatever is already there. What that means for how you run a rollout.
read →Lessons from running three agents in production for real businesses: agents fail on context, tools are contracts, and guardrails are architecture.
read →If you're working on agentic development, AI platform architecture, or figuring out what AI actually changes for engineering organisations — I'm always glad to compare notes.