Senior Backend Engineer — Low-Latency AI Search
Summary
Senior backend engineer at Nebius in London building low-latency, high-throughput runtime services for a novel search engine designed for agentic AI consumption. Day to day you work on the critical path of real-time search, integrating retrieval/ranking with indexing and ML teams, optimizing CPU/memory usage, and ensuring production observability and reliability.
Nebius is seeking a Senior Software Engineer in the United Kingdom to join the runtime systems of a novel search engine crafted for agentic AI consumption. You will build low-latency, high-throughput services that handle real-time search queries on the critical path, shaping performance and efficiency across the stack.
You will collaborate with indexing and ML teams to integrate retrieval and ranking components, optimize CPU/memory usage, and ensure observability and reliability in production
