Staff Software Engineer - Low-Latency AI Search

Nebius Group; London (KY); On-site; USD 140,000 - 190,000; Full time

Benefits offered by this job

Competitive compensation

Career growth

Flexible work options

Ownership culture

Collaborative environment

Impactful AI projects

International teams

Job summary

Nebius Group is building a fast, agent-native search platform as part of a cloud AI infrastructure. The Staff Software Engineer will work on runtime systems that power low-latency, high-throughput query handling at scale, shaping the critical path of real-time search requests.

You will optimize data access, CPU and memory usage, and observability while collaborating with indexing and ML teams to integrate retrieval and ranking components.

Qualifications

• 8+ years of experience as a software engineer on production backend systems.
• Strong hands-on with C++ or Rust in real-world services.
• Experience building high-load, low-latency systems handling thousands of RPS.
• Systems-level understanding of CPU, memory, networking, and data access.
• Proven production deployment, debugging, and rollback experience.
• Ability to design end-to-end request flows across components.

Responsibilities

• Design, implement, and operate core runtime services for serving search queries at scale.
• Optimize request flows, including query processing and response assembly.
• Maintain performance and predictability under high load.
• Tune CPU/memory usage in critical paths.
• Ensure observability with logs, metrics, traces.
• Collaborate with indexing and ML teams to integrate retrieval components.
• Support experimental rollouts and benchmarking.

Skills

8+ years backend

C++

Rust

High-load systems

End-to-end thinking

Cross-team collaboration

Job description

Nebius Group is building a fast, agent-native search platform as part of a cloud AI infrastructure. The Staff Software Engineer will work on runtime systems that power low-latency, high-throughput query handling at scale, shaping the critical path of real-time search requests.

You will optimize data access, CPU and memory usage, and observability while collaborating with indexing and ML teams to integrate retrieval and ranking components.