TrueLayer is a UK-based open banking fintech that provides instant, bank-authenticated payments for online merchants.
<div class="content-intro"><h2>Who we are:</h2> <p>TrueLayer is Europe’s fastest-growing Pay by Bank network. We power smarter, safer and faster payments by combining real-time bank payments with financial and identity data. E-commerce, iGaming and Financial Services businesses use our products to onboard new users, accept money and make payouts in seconds, and at scale. Live across 22 countries and with 1 new user joining TrueLayer’s Pay by Bank network every 3 seconds, we’re in a very exciting growth stage. This is why we’re expanding the team across our offices in London, Milan, and Dublin.</p> <p>Listed in Sifted as one of the 100 fastest growing start-ups in UK & Ireland, and CNBC’s World Top Fintech Companies, we’re trusted by industry leaders like RyanAir and Just Eat Takeaway for continued innovation within our payment products. To date, we’ve raised over $300 million from world-renowned investors including Stripe, Tiger Global, Northzone, and Tencent. But this is just the beginning.</p> <p>We’re looking for people who are excited about joining the Pay by Bank revolution and helping us change the way the world pays. Could this be you? </p></div><h2>Description</h2> <p>TrueLayer is making a deliberate, CTO-led investment in agentic engineering. We are building a new team — Agentic Engineering Enablement — with a focused mission: pave the way for AI agents to succeed across TrueLayer's engineering organisation. Every bottleneck that slows an agent down is a problem to solve. Every piece of tribal knowledge locked in a Slack thread or an engineer's head is an opportunity to unlock.</p> <p>As a Senior Agentic Enablement Engineer, you will be a core pillar of this team. Working closely with the CTO, you will own significant components of the agentic platform — from context engineering and tooling to evaluation systems and CI/CD — and build them into reliable, production-grade infrastructure. You will also help establish engineering norms and best practices for the team and the wider organisation.</p> <p><strong>What does good look like in Year One?</strong></p> <p>Agents routinely land coordinated changes across multiple repos and services, run e2e tests, and deploy behind guardrails without a human in the loop.</p> <p> </p> <p><strong>What we expect from you as a Senior Agentic Enablement Engineer:</strong></p> <p><strong>Build and maintain the agent harness</strong></p> <ul> <li>Write, maintain, and version AGENTS.md files, system prompt libraries, and skill definitions across the codebases and workflows that matter to TrueLayer. Treat this as infrastructure, not documentation.</li> <li>Surface tribal knowledge from across engineering and convert it into structured, agent-consumable artefacts: ADRs, runbooks, coding conventions, decision trees, and system maps.</li> <li>Design and operate MCP servers that give agents safe, real-time access to TrueLayer's internal systems, APIs, databases, CI outputs, incident history, and deployment state.</li> <li>Build and maintain TrueLayer's internal tool library: structured, versioned, testable agent capabilities that encode how we build, test, review, and operate software.</li> </ul> <p><strong>Pave golden paths</strong></p> <ul> <li>Build reusable, opinionated golden paths, starter templates, orchestration patterns, and reference workflows, so every new agent capability is reliable and measurable by default rather than bespoke.</li> <li>Encode the safe way to do something as the easy way to do it. If the golden path is harder than building from scratch, something needs to change.</li> <li>Version and maintain these paths as products with adoption metrics and clear contracts.</li> </ul> <p><strong>Evolve CI/CD for agent-scale workloads</strong></p> <ul> <li>Architect and operate CI/CD pipelines (GitHub Actions, Kubernetes, cloud runners) capable of handling the throughput of multi-agent workflows without becoming a bottleneck.</li> <li>Reduce CI latency through remote execution, caching, parallelisation, and test impact analysis.</li> <li>Build and maintain ephemeral, sandboxed development environments that agents can provision and tear down autonomously.</li> <li>Automate recurring manual tasks: flaky test quarantine, dependency updates, PR triage, and changelog generation.</li> </ul> <p><strong>Design the eval and oversight layer</strong></p> <ul> <li>Design and maintain an evaluation harness: regression suites, benchmark sets, and task-specific evals for every agent capability shipped internally.</li> <li>Define and instrument agent health metrics: token spend, tool call reliability, output drift, and cost per task.</li> <li>Run structured experiments on agent configurations, prompt variants, and tooling choices — grounded in real metrics.</li> <li>Define oversight policies: human-in-the-loop checkpoints for high-risk actions, failure detection, loop detection, and hard cost ceilings. In a regulated payments environment, ungoverned agent access to production systems is a liability.</li> <li>Build guardrails and permission boundaries so agents operate with least-privilege, auditable access to internal systems by default.</li> </ul> <p><strong>Contribute to team and engineering standards</strong></p> <ul> <li>Contribute to the architecture of the agentic platform and participate actively in key technical decisions.</li> <li>Share work, learnings, and setbacks openly. Document thoroughly. Run workshops that help engineers move from sceptics to confident users.</li> <li>Track what is working in the industry and translate it into TrueLayer-specific approaches and playbooks.</li> </ul> <p> </p> <h3><strong>About you:</strong></h3> <ul> <li>You are genuinely AI-pilled. Not someone who has read about this: someone who has restructured their engineering workflow around AI agents and can explain exactly why, what broke, and what you fixed.</li> <li>You are actively building with AI agents — not just using AI-assisted tools occasion