Senior Software Engineer - Search Application (Agentic Search)

Nebius · Israel · Engineering

Posted 2026-09-30

Apply for this role →

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

Work with data analysts and product managers to translate product and quality goals into concrete backend behavior and measurable metrics

You may be a good fit if you:

5+ years of experience building product critical backend services

Strong Go and Python Experience

Experience with large-scale distributed systems (5k+ RPS, billions of events, high-throughput pipelines)

Understanding of Information Retrieval flows and pipelines

Experience operating production systems and debugging failures in distributed environments

Strong understanding of scalability, fault tolerance, and resource management

Are interested in either a strong senior IC role or a role with significant technical leadership and ownership.

Apply for this role →

← Back to all jobs