Senior Full-Stack Engineer - AI Agent Platform

Overview

We're building an AI-powered financial crime investigation platform that's transforming how Ebury's compliance teams work. Our AI agents will process thousands of screening cases, reducing analyst workload while maintaining regulatory standards. We're looking for a Senior Full‑Stack Engineer to help us scale our platform and raise the engineering bar. You'll architect and deliver complex features across the entire stack—from React frontends to Python backends to LLM integrations—while mentoring teammates and shaping our technical direction.

This is a unique opportunity to work at the intersection of AI/ML, fintech, and compliance—building production AI systems that handle real financial crime investigations at scale.

• Architect and build end‑to‑end features across our React frontend and FastAPI backend, making sound technical decisions that balance speed with maintainability.
• Design AI agent workflows using Lang Graph for screening automation, RAG pipelines, and multi‑agent orchestration.
• Lead technical initiatives—own complex features from design to production, breaking down ambiguous problems into actionable work.
• Integrate complex data sources (internal APIs, third‑party services like Lexis Nexis, data warehouse) with robust error handling and observability.
• Improve platform reliability—implement monitoring, alerting, and performance optimizations for production AI systems.
• Mentor and uplift junior and mid‑level engineers through code reviews, pairing, and technical guidance.
• Shape engineering practices—contribute to architecture decisions, coding standards, and team processes.
• Collaborate cross‑functionally with Product, Design, Compliance, and other engineering teams to deliver impactful solutions.

• React, Type Script, Material‑UI
• Module Federation (Micro‑frontend architecture)
• Vite, Vitest

• Python 3.13, FastAPI
• Lang Graph (AI agent orchestration)
• Llama Index (RAG/vector search)
• AWS Bedrock
• Dynamo
  
  DB, Open Search Serverless

• AWS (ECS Fargate, Lambda, API Gateway, S3)
• Terraform, Git Hub Actions
• Docker, Kubernetes
• Sentry, Langfuse (LLM observability)

• Greenfield AI Product:
  You'll help shape a product from early stages, not maintain legacy code. Your architectural decisions will have lasting impact.
• Technical Leadership:
  Drive technical direction for a growing team. Mentor engineers and establish patterns that scale.
• Cutting‑Edge AI:
  Work with the latest LLM technologies in production—Lang Graph, RAG, multi‑agent systems, and more.
• Real Impact:
  Our AI agents process thousands of compliance cases. You'll see your work making a difference within weeks.
• Startup‑within‑Enterprise:
  Small, autonomous team with startup speed, backed by enterprise resources and stability.

• 5+ years of professional software engineering experience.
• Strong React + Type Script skills—architect complex frontend applications with good state management, performance, and testing.
• Strong Python backend experience—FastAPI, Django, or Flask with async programming, clean architecture, and production‑grade code.
• System design skills—design scalable, maintainable systems and articulate trade‑offs clearly.
• API design expertise—REST, Web Sockets/SSE, and understanding of distributed systems patterns.
• Database proficiency—SQL and No
  
  SQL (Dynamo
  
  DB, Postgre
  
  SQL, Open Search), including query optimization and data modeling.
• Testing mindset—write comprehensive tests and advocate for quality across the team.
• Ownership mentality—take features from idea to production, proactively identifying and solving problems.
• Strong communication—explain complex technical concepts to engineers and non‑engineers, and write clear documentation.
• Mentorship ability—enjoy helping others grow and have experience guiding less experienced engineers.

• LLM/AI experience—Lang Chain, Lang Graph, RAG pipelines, prompt engineering, or fine‑tuning.
• Production AI systems—experience with LLM observability (Langfuse), token management, streaming, and reliability patterns.
• AWS expertise—Lambda, ECS, Dynamo
  
  DB, Open Search, Bedrock, or similar cloud services.
• Streaming architectures—SSE, Web Sockets,…