Senior Full-Stack Engineer — Flow (AI Agent Platform)

Location: London, Victoria Office Work Pattern: Hybrid (4 days office, 1 day remote) Team: Flow (Core AI Infrastructure)

Ebury helps ambitious businesses unlock global growth, and we take the same approach with our people. We encourage innovation and movement, collaboration and problem-solving, and foster an environment where everyone can feel they belong, are valued, supported, and empowered to succeed.

If you’re a collaborator who wants to help transform how businesses operate globally, get in touch—we’d love to discuss how Ebury can accelerate your career so you can shape the future.

About the Role

Flow is our internal AI agent platform. This isn’t just a basic chatbot plugged into a help center—it’s core agentic infrastructure that integrates with our data warehouse, services, and central systems to execute complex work on behalf of the business. Flow powers both internal and external workflows, replacing traditional ticketing queues with instant, intelligent actions.

We’re looking for a Senior Full-Stack Engineer to help us transition Flow from a fast-moving internal product into durable, productionized platform infrastructure. You’ll own complex features end-to-end—even across agent workflows, reasoning UIs, hybrid cloud integrations—while you raise the engineering bar and shape the technical direction of a small, autonomous team.

This role sits at the intersection of agentic AI and live operational workflows within a regulated fintech environment. The surface area spans the entire company, and your impact will be visible within weeks.

What You’ll Do

• Build action-oriented agent workflows by designing multi-step orchestration, tool use, and retrieval mechanisms grounded in our data stores using the Strands Agents SDK.
• Architect end-to-end features, spanning a React/TypeScript frontend, a Python/FastAPI backend, and balancing rapid innovation with platform stability.
• Own the reasoning layer: Extend the chain-of-thought UI to ensure explainability—regulatory compliance demands tracing decisions before implementation.
• Make agents measurable and reliable by leveraging and extending Ragas (for evaluation) and Langfuse (for observability).
• Define custom evaluation strategies, datasets, automated benchmarks, and execution pipelines to ensure improvements are evidenced.
• Integrate internal systems, data warehouses, email, and cross-cloud GCP/AWS services with error handling, retries, and distributed tracing.
• Industrialize prototypes, driving a partners-to-platform pipeline through DevOps, testing, and production rollouts.
• Mentor and uplift mid-level engineers via code reviews, paired coding, and pattern standardisation.
• Collaborate cross-functionally with Product, Ops, Trading, and Treasury to pinpoint and prioritise automation opportunities (and ruthlessly cut the rest).