Backend Engineer – AI Infrastructure & Data Platforms

About the role

We are scaling the backend systems that power our AI‑driven product suite, including retrieval‑augmented generation pipelines, real‑time inference APIs and vector search infrastructure. As a Backend Engineer you will own the services that sit between large language model providers and our customer‑facing products, ensuring reliability, low latency and cost efficiency at scale.

Key responsibilities

• Design, build and maintain APIs serving LLM‑powered features for 500k+ monthly active users.
• Develop and optimise RAG pipelines, including chunking, embedding generation and vector store management.
• Architect event‑driven micro‑services using Kafka or SQS for high‑volume inference requests.
• Implement observability and token‑usage cost tracking across multiple LLM providers.
• Manage database performance for relational (PostgreSQL) and vector (pgvector/Pinecone) workloads.
• Collaborate with ML engineers on model‑serving infrastructure and prompt‑caching strategies.
• Drive API versioning and maintain backwards compatibility as the product evolves.

Required profile

• 4+ years of backend development experience, with at least 1 year on LLM/AI‑integrated systems.
• Strong understanding of asynchronous architecture and distributed systems.
• Experience with vector databases or semantic search implementations.
• Comfortable working directly with LLM APIs, handling rate limits, streaming responses and token cost optimisation.

Required skills

• Python (FastAPI)
• Go
• TypeScript / Node.js
• PostgreSQL, Redis
• Pinecone or pgvector
• AWS (ECS, Lambda, SQS/SNS)
• Docker, Kubernetes, Terraform
• Kafka or SQS
• LangChain, LlamaIndex, vLLM
• Anthropic and OpenAI APIs
• Datadog, Grafana, OpenTelemetry
• GitHub Actions, ArgoCD

What we offer

• 25 days holiday plus bank holidays.
• Private healthcare (Vitality).
• £1,000 annual learning budget.
• Hybrid working with full work‑from‑home equipment provided.