Here it is:
-----------------------------------
Principal Platform Engineer Belfast (Hybrid) | Permanent | Confidential Client
If you're not based in Belfast or within commuting distance, this one's not for you.
Our client is a fast-scaling fintech building the next generation of payment infrastructure. They're merchant-first, engineering-led, and genuinely obsessive about outcomes over process. Small teams, real autonomy, hard problems.
They're hiring a Principal Platform Engineer to own the design and delivery of a suite of Model Context Protocol (MCP) servers - the trusted, governed gateway between AI agents and their core payments platform.
This is a hands-on principal role. You'll set technical direction and write production code, not just review it.
What you'll be doing:
* Owning the architecture and delivery of MCP servers that expose platform data and capabilities to AI agents and internal developer tooling
* Designing the transport and session model (Streamable HTTP), including stateful sessions for progress streaming, subscriptions, sampling, and user elicitation flows
* Implementing robust OAuth-based authentication and authorisation, integrated with the company's identity provider, with least-privilege, per-request data scoping
* Designing and operating the edge and gateway layer - Cloudflare Workers and Durable Objects - for token validation, JWKS caching, routing, and session state
* Defining standards, patterns, and reusable libraries so other teams can build additional MCP servers quickly, consistently, and securely
* Embedding security and compliance into every layer - this is a high-trust surface over sensitive payment data
* Driving observability, performance, and reliability across the stack, including logging, tracing, rate limiting, and graceful degradation
* Mentoring engineers, reviewing designs and code, and acting as a technical leader across a domain that is new, fast-moving, and security-sensitive
What they're looking for:
* 8 to 10 years in software engineering, with a track record of owning systems end to end
* Deep server-side expertise in TypeScript/Node.js or Python - both are actively used here
* Strong, practical understanding of the Model Context Protocol - defining tools, resources, and prompts; designing well-typed schemas; writing tool descriptions that drive reliable model behaviour
* Solid grounding in LLM tool-use and agentic patterns, including how models select and invoke tools, manage context, and handle multi-step interactions
* Hands-on experience with OAuth 2.0, OIDC, JWT validation, and identity provider integration
* Experience deploying and operating services at the edge or in serverless environments - Cloudflare Workers, AWS Lambda, Cloud Run, or similar
* Security-first mindset; PCI DSS awareness is a strong plus
* Awareness of AI-specific security concerns - prompt injection, over-broad tool permissions, and safe handling of model-driven actions
* Comfortable operating as a team of one or scaling up to lead a broader group
* BS or MS in Computer Science or equivalent practical experience