Nebius · posted · checked
Senior Software Engineer – Search Application (Agentic Search)
PythonOn-site · IsraelSenior
Who can apply
On-site · Israel
Location: Tel Aviv, Israel
About Nebius:
Nebius is leading a new era in cloud infrastructure for the global AI economy. We are building a full-stack AI cloud platform that supports developers and enterprises from data and model training through to production deployment, without the cost and complexity of building large in-house AI/ML infrastructure.
Built by engineers, for engineers. From large-scale GPU orchestration to inference optimization, we own the hard problems across compute, storage, networking and applied AI.
Listed on Nasdaq (NBIS) and headquartered in Amsterdam, we have a global footprint with R&D hubs across Europe, the UK, North America and Israel. Our team of 1,500+ includes hundreds of engineers with deep expertise across hardware, software and AI R&D.
We are looking for a Senior Software Engineer to work on the core search application powering our agentic search platform.
In this role, you will build and operate a high-scale, latency-sensitive API that sits at the center of the search request flow. The system orchestrates multiple retrieval capabilities, ranking components, and downstream services to serve thousands of search requests per second while balancing search quality, latency, reliability, and infrastructure cost.
In this position, your responsibility will be to
Design, implement, and operate core backend components of a search orchestration system, spanning online services and background data pipelines.
Build well-tested services and pipelines with clear responsibilities and interaction contracts, while remaining flexible as the system evolves
Define and implement observability primitives, including structured logs, metrics, traces, and quality signals for both online and offline components
Support experimentation and iteration by enabling feature flags, controlled rollouts, and online experiments
Track throughput, latency, and resource usage across the system, and improve performance or cost efficiency when business needs require it
Collaborate closely with ML engineers to integrate search quality improvements to the system, while keeping ML logic decoupled from core system internals
Monitor resource usage, bandwidth consumption, and infrastructure cost