Backend Engineer; AI Platform

Backend Engineer (AI Platform) - London

£80k–£100k + EMI equity

We’re hiring a Backend Engineer to build the core infrastructure behind Revax’s AI-native platform for professional services.

You’ll design, optimise, and scale the systems that power multi-agent drafting, knowledge graphs, and auditable AI workflows used by accountants, tax advisors, and consultants at leading firms. This is not a “ticket-taking” role – you’ll work directly with the founders, own critical backend services end-to-end, and help define how AI systems are built responsibly in regulated domains.

If you enjoy designing clean APIs, scaling Python services, and building systems that actually ship to paying customers, this role is for you.

£80,000–£100,000 base + EMI equity

London

Revax is building a new class of AI-native software for tax advisory firms.

Today, professional services teams spend countless hours drafting, reviewing, and re-drafting work – constrained by fragmented knowledge, manual workflows, and brittle tooling. We turn a firm’s own expertise into structured, auditable, AI-powered systems that draft, analyse, and explain deliverables with full provenance.

We’re a fast-moving, well‑funded startup backed by leading angels, already working with major firms, and building at the intersection of AI agents, knowledge graphs, and real‑world enterprise workflows.

• Build and optimise databases for complex, real‑world data
• Design and implement APIs using FastAPI for AI workflows and product features
• Build and scale Lang Graph‑based multi‑agent systems with checkpointing, retries, and observability
• Integrate and scale vector search, knowledge graphs (Neo4j), and associated retrieval pipelines into production services
• Deploy and operate GPU‑backed services for AI workloads (e.g. inference, embeddings, or agent pipelines) in production

• Deploy services on GCP (Cloud Run / GKE) or equivalent cloud infrastructure
• Improve performance, reliability, and cost efficiency (latency, throughput, retries, backoffs)
• Implement security‑first patterns: auth flows, service‑to‑service auth, IAM, and access controls
• Help prepare the platform for enterprise customers (SSO, auditability, compliance ready patterns)

• Shape system architecture and API design alongside full‑stack and ML engineers
• Translate ambiguous product ideas into robust backend implementations
• Iterate quickly based on real customer usage and feedback

• 2-3 years building backend systems for real users
• Production experience with FastAPI (or similar modern Python frameworks)
• Solid understanding of API design, Postgre
  
  SQL, and distributed systems fundamentals
• Experience deploying and operating services on cloud infrastructure (GCP, AWS, and Azure)
• High ownership mindset: you care deeply about reliability, correctness, and outcomes

• Experience with Lang Graph, RAG pipelines, vector databases, or knowledge graphs
• Familiarity with Neo4j or graph‑based data modelling
• Experience working on AI‑native or agentic systems
• Comfort working in early‑stage startups with ambiguity and speed
• Experience deploying and working with GPU services for AI workloads

• Exposure to professional services, finance, tax, or regulated workflows
• You actively use modern AI coding tools (Cursor, Claude Code, etc.)
• Strong instincts for developer experience and internal tooling

• Real ownership over core backend infrastructure
• Work directly with founders on high‑impact technical decisions
• AI‑native product with real customers and immediate feedback
• Modern stack:
  Python, FastAPI, Lang Graph, Postgres, Supabase, Neo4j, GCP
• Meaningful early‑stage equity: we hire owners, not passengers
• A lean, low‑ego, high‑drive team that ships fast and cares about their work

• London based (strong preference for in office collaboration)
• Visa sponsorship available