Staff Software Engineer – Runtime for Agentic Search

About the role

Nebius is seeking a Staff Software Engineer to own the runtime systems of its novel, agent‑native search platform. You will build low‑latency, high‑throughput services that power real‑time search queries for AI agents.

Key responsibilities

• Design, implement and operate core runtime services that serve thousands of requests per second under strict latency budgets.
• Optimise request flows, query processing, retrieval orchestration and response assembly for performance and predictability.
• Develop observability primitives (structured logs, metrics, traces) and monitor throughput, latency and resource usage.
• Collaborate with indexing and ML teams to integrate retrieval and ranking components while keeping ML logic decoupled.
• Support experimentation through controlled rollouts and rigorous benchmarking.

Required profile

• 8+ years of experience building production backend systems.
• Hands‑on expertise in C++ or Rust for high‑load services.
• Proven track record of operating low‑latency, high‑throughput systems in production.
• Deep understanding of CPU, memory, networking and data‑access performance at a systems level.
• Ability to think end‑to‑end about request flows and balance correctness, latency and development velocity.

Required skills

• C++
• Rust
• DBMS internals (open‑source or SaaS)
• Cloud infrastructure
• High‑load web applications / large‑scale APIs
• Performance‑critical systems and low‑level tuning

What we offer

• Competitive compensation
• Career growth and learning opportunities
• Flexibility and ownership of work
• Collaborative, innovative culture
• Impactful AI projects in an international environment