As a Software Engineer at REVAX, you will work directly with founders to build and scale multi-agent AI systems. You will own features end-to-end, from prototyping LangGraph-based agents to production hardening on GCP. This role is central to transforming how major tax advisory firms research and draft complex deliverables using structured, transparent AI.
Software Engineer at REVAX
Join REVAX, a seed-stage London startup backed by leading institutions, as a Software Engineer building the future of AI-native tax advisory. You'll work directly with the founders to scale multi-agent systems using LangGraph, Neo4j, and FastAPI. This role offers the unique opportunity to own end-to-end features in a high-stakes regulated domain, shipping production-grade AI to major firms. If you have 2-3 years of experience, a passion for agentic systems, and thrive in a high-ownership startup environment, apply now to help us redefine professional services from the ground up.
About this role
Role overview
About the company
Revax is a seed stage startup (announcement upcoming) delivering AI research and drafting tools to accountants, tax advisors, and professional service firms. It connects to a firm's in-house knowledge using knowledge graphs, employs deep research agents with custom tools to draft client deliverables mimicking advisor workflows, provides citations for fact-checking, supports diagramming, exports to PowerPoint/Word, and integrates live legislative data.
What you'll do
What you will do
- Architect and implement multi-agent systems using LangGraph, incorporating retrieval pipelines, vector search, and Neo4j knowledge graphs for complex data modelling.
- Design and scale performant FastAPI services on Google Cloud Platform, ensuring high reliability, observability, and cost-efficiency for AI-driven workflows.
- Build enterprise-grade features including IAM, multi-tenant isolation, and audit trails to meet the rigorous security requirements of major advisory firms.
Who you are
Who this is a fit for
- Has 2-3 years of experience building production software, including at least one year within a fast-paced startup environment.
- Demonstrates deep technical proficiency with modern Python, FastAPI, and AI technologies like RAG pipelines, vector databases, or LangGraph systems.
- Exhibits a high-ownership mindset and leverages modern AI coding tools like Cursor or Claude Code to ship high-quality code at speed.
Why this role
Why this role is remarkable
- Work at the cutting edge of agentic AI, building production-grade multi-agent systems using LangGraph and knowledge graphs for highly regulated domains.
- Join a high-velocity, technical founding team at the seed stage, backed by top-tier institutions and already delivering value to major professional services firms.
- High-impact ownership where you define the engineering standards and security patterns required to sell sophisticated AI products to enterprise clients.
Jack & Jill
How Jack & Jill work together
Meet Jack
Jack gets to know what you're great at and what you want next, then searches 15 million jobs daily and helps you discover roles at companies like this.
How does this work?
Jack’s an AI agent for job searching and career coaching. He works for you.
Jill is the AI recruiter working for the company. She recruits from Jack’s network.
If it’s a match and the company wants to meet you, they’ll make the intro. In the meantime, if you’d like, Jack will send you excellent alternatives.