Backend Engineer

We're looking for a Backend Engineer to build and operate the AI infrastructure that powers our product.

You'll own the inference and orchestration layer between foundation models and our users, designing production systems that are fast, reliable and scalable. This role is focused on solving real engineering problems around latency, throughput, observability and distributed systems—not building model architectures.

What You'll Do

• Build and maintain backend services powering AI features in production
• Design inference pipelines and orchestration layers for LLM-based applications
• Develop scalable APIs used by mobile and desktop clients
• Optimise latency, throughput and cost using caching, batching and streaming
• Own production monitoring, logging, alerting and incident response
• Work closely with ML and frontend engineers to deliver reliable AI experiences

What We're Looking For

• Strong backend engineering experience with Python
• Experience building and operating high-throughput, low-latency production systems
• Understanding of distributed systems and microservice architectures
• Experience with AI inference, LLMs, embeddings or similar AI technologies
• Strong debugging and performance optimisation skills
• Comfortable working in fast-moving product environments