> Markdown version of [/jobs/ext/2729553-full-stack-engineer-flow-ai-agent-platform](https://www.wearedevelopers.com/jobs/ext/2729553-full-stack-engineer-flow-ai-agent-platform). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Full-Stack Engineer - Flow (AI Agent Platform) - **Company:** Ebury - **Location:** London, UK (Remote available) - **Experience:** Expert - **Contract:** Permanent contract - **Skills:** Multitier Architecture, Application Programming Interfaces (APIs), Artificial Intelligence, Amazon Web Services, Amazon S3, Application Integration Architecture, Code Review, Data Stores, Data Warehousing, Django Web Framework, Github, Python (Programming Language), Message Broker, NoSQL, Pair Programming, Performance Tuning, Query Optimization, Cloud Services, Standard Sql, Software Engineering, System Testing, TypeScript, WebSocket, ReactJS, Flask (Web Framework), Delivery Pipeline, Large Language Models, Multi-Agent Systems, Backend, Fastapi, Event Driven Architecture, Webpack, Production Code, Data Analytics, AWS Fargate, Front End Software Development, Virtual Agents, Asynchronous Programming, Functional Programming, Api Gateway, JestJS, Terraform, Dynatrace, Docker - **Published:** September 5, 2026 - **Apply:** https://startup.jobs/full-stack-engineer-ai-ebury-8687537 ## About the Role * React, TypeScript * Micro-frontend architecture * Chain-of-Thought / Agent-reasoning UI * Vite, Vitest Backend & AI * Python, FastAPI * Strands Agents SDK (Agent Orchestration) * AWS Bedrock * RAG / Advanced Retrieval * Ragas (Evaluation), Langfuse (LLM Observability), * 5+ years of professional software engineering experience. * Strong Python Backend Expertise: Deep experience with FastAPI (or Django/Flask), asynchronous programming, clean architecture, and writing production-grade code. * Strong React & TypeScript Skills: Ability to architect non-trivial frontends with sound state management, performance optimization, and comprehensive testing. * System Design Judgment: A proven track record of designing scalable, maintainable systems and clearly articulating architectural trade-offs. * API & Integration Skills: Proficiency with REST, streaming (SSE/WebSockets), and the real-world complexities of stitching together messy upstream systems. * Data Proficiency: Strong SQL/NoSQL skills, query optimization, and data modeling. * Testing & Ownership Mindset: You treat testing as a core part of the development lifecycle and proactively drive features from ambiguous ideas to production. * Excellent Communication: Ability to explain technical decisions to both engineers and non-technical stakeholders, alongside a passion for writing useful documentation., * Agentic AI Experience: Hands-on experience with agent orchestration (Strands, LangGraph, AutoGen, or similar), RAG, tool use, and context engineering. * Production LLM Systems: Familiarity with LLM observability (Langfuse), evaluation (Ragas), token/cost management, and reliability patterns. * AWS Depth: Experience with Lambda, ECS, Bedrock, or equivalent cloud services (cross-cloud exposure is a major plus). * Event-Driven Architectures: Experience with event streaming and message brokers. * Regulated Environments: Experience working within fintech, compliance, or similar sectors with strict data-residency and auditability constraints. * Micro-frontends & IaC: Experience with micro-frontend architecture and Infrastructure as Code (Terraform/CDK). ## Description Flow is our internal AI agent platform. This isn't a basic chatbot bolted onto a help center; it is core agentic infrastructure that reaches across our data warehouse, services, and central systems to execute complex work on behalf of the business. Flow powers both internal and client-facing workflows, delivering true automation and replacing traditional ticketing queues with instant, intelligent actions. We are looking for a Senior Full-Stack Engineer to help us transition Flow from a fast-moving internal product to durable, productionized platform infrastructure. You will own complex features end-to-end-including agent workflows, reasoning UIs, and cross-system integrations-while raising the engineering bar and shaping 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 is the entire company, and your impact will be visible within weeks. What You'll Do * Build Action-Oriented Agent Workflows: Design multi-step orchestration, tool use, and retrieval grounded in our data stores using the Strands Agents SDK. * Architect End-to-End Features: Own development across a React/TypeScript frontend and Python/FastAPI backend, balancing rapid iteration with platform maintainability. * Own the Reasoning Layer: Extend our Chain-of-Thought UI to ensure explainability. In a regulated environment, showing why an agent made a decision is a core feature, not a nicety. * Make Agents Measurably Reliable: Build and extend our evaluation harness (Ragas) and observability platform (Langfuse, with session continuity) so we ship changes based on evidence, not vibes. * Define Evaluation Strategies: Build custom evaluators, datasets, benchmarks, and automated regression suites to catch quality regressions before they hit production. * Integrate Systems & Clouds: Connect internal APIs, data warehouses, email, and cross-cloud GCP/AWS services with robust error handling and distributed tracing. * Industrialize Prototypes: Drive the discover * industrialize * productionize lifecycle, turning promising AI prototypes into hardened, daily-deployed services on CD pipelines. * Mentor & Lead: Uplift mid-level engineers through code reviews, pair programming, and establishing scalable engineering patterns. * Collaborate Cross-Functionally: Partner with Product, Ops, Trading, and Treasury to identify high-value workflows worth automating (and ruthlessly deprioritize the ones that aren't)., * AWS (ECS Fargate, Lambda, API Gateway, S3) with cross-cloud GCP integration * Terraform, GitHub Actions * Docker * Event-driven integration patterns, Ebury only accepts applications via official Ebury channels. We will only contact you from an @ebury.com domain. Always check the emails you receive from us, and note that we will never request payment for any part of the recruitment process. Stay safe and report suspicious activity. Notice to Recruitment Agencies and Search Firms: Ebury does not accept unsolicited resumes, CVs, or candidate profiles from recruitment agencies or search firms without signed written Ebury recruitment terms in place for a specific role. Any unsolicited applications will be considered the sole property of Ebury. Ebury will not be responsible or liable for any placement fees or costs associated with unagreed candidate submissions or subsequent hires. AI Transparency Statement: Ebury uses Artificial Intelligence (AI) and automated tools to help streamline certain parts of our recruitment process, however, these tools are strictly for administrative efficiency. All hiring decisions, including application reviews, shortlisting, and final selections are evaluated and conducted by human talent acquisition professionals and hiring managers. ## Related Videos - [Docker Compose: Rediscovered](https://www.wearedevelopers.com/videos/1978-docker-compose-rediscovered) - [Leveraging Real time data in FSIs](https://www.wearedevelopers.com/videos/806-leveraging-real-time-data-in-fsis) - [Building a Multi-Agent Orchestration Engine That Actually Follows the Rules](https://www.wearedevelopers.com/videos/100159-building-a-multi-agent-orchestration-engine-that-actually-follows-the-rules) - [Docker build without Docker](https://www.wearedevelopers.com/videos/100114-docker-build-without-docker) - [NoSQL Data Modeling for Front-end Developers](https://www.wearedevelopers.com/videos/297-nosql-data-modeling-for-front-end-developers) - [Agentic employees in world's most downloaded FinTech app](https://www.wearedevelopers.com/videos/100123-agentic-employees-in-world-s-most-downloaded-fintech-app) ## Related Articles - [From Prototype to Production: Build AI Agents with This Free 4-Course Learning Path](https://www.wearedevelopers.com/magazine/655-from-prototype-to-production-build-ai-agents-with-this-free-4-course-learning-path) - [Dev Digest 121 - AI goes offline](https://www.wearedevelopers.com/magazine/456-dev-digest-121-ai-goes-offline) - [Dev Digest 120 - Apple and peers](https://www.wearedevelopers.com/magazine/455-dev-digest-120-apple-and-peers) - [Dev Digest 132 - Binging WADFlix?](https://www.wearedevelopers.com/magazine/473-dev-digest-132-binging-wadflix) - [Graph and AI Trends 2026: Why Is AI Running but Not Yet Delivering?](https://www.wearedevelopers.com/magazine/680-graph-and-ai-trends-2026-why-is-ai-running-but-not-yet-delivering) - [Navigating the AI Shift](https://www.wearedevelopers.com/magazine/629-navigating-the-ai-shift)