The role
The company is building an AI operating system for complex enterprise software environments. They use agentic AI to automate the analysis and documentation work that gates large‑scale migrations and modernization efforts. It’s a hard problem: mapping programs, tables, and dependencies inside bespoke enterprise systems. Founded by experienced operators from top‑tier tech companies, they’re already working with leading global enterprises and are backed by leading investors.
You’ll join a small, talent‑dense backend team. This isn’t a ticket‑taker role. You’ll own significant pieces of the core platform, from large‑scale batch job infrastructure to the LLM gateway and enterprise‑grade auth/observability. Expect high autonomy and real surface area from day one. The team operates with lean loops and a relentless quality bar. You’re here to solve problems end‑to‑end, not just implement specs.
The work
- Design and build large‑scale batch processing infrastructure, handling tens of millions of lines of customer code per tenant.
- Develop and optimize the LLM gateway, managing token throughput, provider failover, and quota across multiple models for real‑time and async workloads.
- Own critical platform components like multi‑tenant authentication, observability, and security, ensuring enterprise‑grade reliability.
- Build internal tooling and APIs that measurably accelerate product development and maintain a high engineering velocity.
- Push the boundaries of the current stack (Kotlin, TypeScript, Azure, Terraform, Temporal, Postgres) to solve complex, evolving technical challenges.
What you bring
- 3+ years of backend engineering experience, with significant platform or infrastructure ownership in a high‑velocity startup environment.
- Proven ability to design and build distributed systems, including large‑scale batch processing and queueing, owning problems end‑to‑end.
- Experience with LLM infrastructure at scale: token routing, provider failover, and managing real‑time vs. async patterns.
- A track record of building internal tooling or APIs that demonstrably improved team efficiency, with a strong focus on reliability, observability, and multi‑tenant security.
- Willingness to work in person with the team in Central London five days a week.
As part of the recruitment process at Dex, we process your personal data in accordance with our Privacy Notice for Job Applicants. This notice explains how and why your data is collected and used, and how you can contact us if you have any concerns.
