Ebury - Full stack Engineer - AI
Requirements
• Frontend • React, TypeScript • Micro-frontend architecture • Chain-of-Thought / Agent-reasoning UI • Backend & AI • Python, FastAPI • Strands Agents SDK (Agent Orchestration) • RAG / Advanced Retrieval • Ragas (Evaluation), Langfuse (LLM Observability) • Infrastructure • AWS (ECS Fargate, Lambda, API Gateway, S3) with cross-cloud GCP integration • Terraform, GitHub Actions • Event-driven integration patterns • Must-Haves • 5+ years of professional software engineering experience. • 5+ years • Strong Python Backend Expertise: Deep experience with FastAPI (or Django/Flask), asynchronous programming, clean architecture, and writing production-grade code. • Strong Python Backend Expertise: • 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. • System Design Judgment: • API & Integration Skills: Proficiency with REST, streaming (SSE/WebSockets), and the real-world complexities of stitching together messy upstream systems. • SSE/WebSockets • Data Proficiency: Strong SQL/NoSQL skills, query optimization, and data modeling. • Data Proficiency: • Testing & Ownership Mindset: You treat testing as a core part of the development lifecycle and proactively drive features from ambiguous ideas to production. • Testing & Ownership Mindset: • Excellent Communication: Ability to explain technical decisions to both engineers and non-technical stakeholders, alongside a passion for writing useful documentation. • Excellent Communication: • Nice-to-Haves • 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. • Production LLM Systems: • AWS Depth: Experience with Lambda, ECS, Bedrock, or equivalent cloud services (cross-cloud exposure is a major plus). • AWS Depth: • Event-Driven Architectures: Experience with event streaming and message brokers. • Event-Driven Architectures: • Regulated Environments: Experience working within fintech, compliance, or similar sectors with strict data-residency and auditability constraints. • Regulated Environments: • Micro-frontends & IaC: Experience with micro-frontend architecture and Infrastructure as Code (Terraform/CDK). • Micro-frontends & IaC: • Ebury delivers sophisticated, integrated solutions — business accounts, hedging, and financing — on a single platform with a seamless workflow. Our success is built on a simple premise and singular purpose: To help businesses operate and scale globally. • Since its founding in 2009, Ebury has always been a fast-growing leader in fintech. Today, we bring together 1,800+ Eburians across nearly 70 cities and we’re always looking to add to our team. • At the heart of our offering is a proprietary platform, purpose-built to help businesses seamlessly streamline and manage global cash flow. We focus on continuous product evolution and innovation to build the infrastructure for borderless growth and help our clients scale at every stage. • The opportunities at Ebury are as diverse as our people, ranging from business development to engineering roles across our tech pillars. • We believe in inclusion. We stand against discrimination in all forms and are against the intolerance of differences that makes us a modern and successful organisation. At Ebury, you can be whoever you want to be and still feel a sense of belonging no matter your story.
Responsibilities
• Build Action-Oriented Agent Workflows: Design multi-step orchestration, tool use, and retrieval grounded in our data stores using the Strands Agents SDK. • Build Action-Oriented Agent Workflows: • Architect End-to-End Features: Own development across a React/TypeScript frontend and Python/FastAPI backend, balancing rapid iteration with platform maintainability. • Architect End-to-End Features: • 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. • Own the Reasoning Layer: • 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. • Make Agents Measurably Reliable: • Ragas • Langfuse • Define Evaluation Strategies: Build custom evaluators, datasets, benchmarks, and automated regression suites to catch quality regressions before they hit production. • Define Evaluation Strategies: • Integrate Systems & Clouds: Connect internal APIs, data warehouses, email, and cross-cloud GCP/AWS services with robust error handling and distributed tracing. • Integrate Systems & Clouds: • Industrialize Prototypes: Drive the discover → industrialize → productionize lifecycle, turning promising AI prototypes into hardened, daily-deployed services on CD pipelines. • Industrialize Prototypes: • Mentor & Lead: Uplift mid-level engineers through code reviews, pair programming, and establishing scalable engineering patterns. • Mentor & Lead: • 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). • Collaborate Cross-Functionally:
Apply in one click
Upload My Resume
Drop here or click to browse · Tap to choose · PDF, DOCX, DOC, RTF, TXT