6 months ago
Amsterdam, Netherlands or London, United KingdomSenior
Responsibilities
- Design, implement, and operate core runtime services for serving search queries.
- Build and optimize query processing, retrieval orchestration, and response assembly flows.
- Develop systems that meet strict latency budgets under high load.
- Optimize CPU, memory, and data access patterns in performance-critical paths.
- Ensure production reliability, observability, and predictability.
- Build well-tested systems with clear boundaries that support architectural evolution.
- Define observability primitives including logs, metrics, traces, and latency breakdowns.
- Monitor and improve latency, throughput, and cost efficiency.
- Collaborate with indexing and ML teams to integrate retrieval and ranking components.
- Support experimentation through controlled rollouts and benchmarking.
Requirements
- 5+ years of experience building production backend systems.
- Strong expertise in C++ or Rust.
- Experience with high-load, low-latency user-facing systems and services handling thousands of requests per second.
- Systems-level understanding of CPU, memory, and networking performance.
- Experience operating production services, handling incidents, and debugging.
- Understanding of distributed systems fundamentals and tradeoffs.
- Ability to think end-to-end about request flows and balance correctness, latency, and development speed.
- Strong collaboration skills across engineering, ML, and product.
- Experience with DBMS and cloud infrastructure is a plus.
- Experience with high-load web applications, large-scale APIs, performance-critical systems, low-level optimization, open-source contributions, competitive programming, CTFs, SHAD or similar programs, conference talks, or technical publications is a plus.
- Coding interviews are part of the hiring process.
Benefits
- Competitive salary and comprehensive benefits package.
- Flexible working arrangements.
- Professional growth opportunities within Nebius.
- Collaborative work environment that values initiative and innovation.
About Nebius
Nebius builds a full-stack AI cloud offering GPU compute, storage, and tools for training and deploying ML models for startups, enterprises, and research labs. It sells consumption-based cloud infrastructure (IaaS/PaaS) and managed services tailored to generative AI workloads, including large-scale model training and inference. The company is headquartered in Amsterdam and operates as an independent provider.