Role Overview
Join a lean backend team at a rapidly growing AI company building an AI operating system for enterprise IT. Own critical platform components: large-scale batch job infrastructure, LLM gateway for token throughput and provider failover, and auth/observability defaults for enterprise reliability. Solve hard foundational problems across tens of millions of lines of customer code, real-time LLM workloads, and multi-tenant security.
Responsibilities
- Design and build core backend platform components enabling rapid engineering shipping.
- Develop and scale batch job infrastructure handling massive data volumes and complex processing.
- Engineer the LLM gateway managing token throughput, provider failover, and quota across diverse models.
- Establish robust auth and observability defaults meeting stringent enterprise reliability and security standards.
- Build internal tooling and APIs that measurably accelerate product development and team efficiency.
Requirements
- 3+ years backend engineering experience with significant ownership over platform/infrastructure components (MVP to scale-up).
- Proven experience designing and implementing distributed systems, including queueing and large-scale batch processing in production.
- Familiarity with LLM infrastructure at scale: token routing, provider failover, real-time vs async patterns.
- Track record building internal tooling or APIs that significantly improved team velocity; treat reliability, observability, and multi-tenant security as first-class concerns.
- Ability to work in person in London five days a week.