Staff Backend Engineer (Low-Latency AI Search)

Nebius Group; Greater London; On-site; GBP 120,000 - 170,000; Full time

Benefits offered by this job

Competitive compensation

Career growth

Flexibility

Collaborative culture

Impactful AI projects

International environment

Job summary

Nebius is seeking a Staff Software Engineer to advance the runtime systems of our agent-native search platform. You will design and operate low-latency, high-throughput services that handle real-time search queries, optimise critical paths, and ensure predictable performance under load.

You will collaborate with indexing and ML teams to integrate retrieval and ranking components while keeping ML logic decoupled from core systems.

Qualifications

• 8+ years of experience in production backend systems
• Strong hands-on expertise in C++ or Rust for high‑load services
• Experience building and operating low‑latency, scalable backends

Responsibilities

• Design, implement, and operate core runtime services for serving search queries at scale
• Build and optimise request flows, including query processing and response assembly
• Develop systems that maintain performance under high load
• Tune CPU, memory, and data access in critical paths
• Ensure reliability, observability, and deterministic performance
• Create well-tested components with clear interfaces and evolving architecture
• Define observability primitives: logs, metrics, traces, latency breakdowns
• Monitor throughput, latency, and resource usage; drive cost/performance improvements
• Collaborate with indexing and ML teams to integrate ranking components
• Support experimentation with controlled rollouts and benchmarking

Skills

Backend experience

C++ or Rust

High-load systems

Performance tuning

Cross-team collaboration

Job description

Nebius is seeking a Staff Software Engineer to advance the runtime systems of our agent-native search platform. You will design and operate low-latency, high-throughput services that handle real-time search queries, optimise critical paths, and ensure predictable performance under load.

You will collaborate with indexing and ML teams to integrate retrieval and ranking components while keeping ML logic decoupled from core systems.