jobs

Senior Software Developer: Models Team (Token Factory)

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 deployme

In inglese

Company

Nebius

Location

Amsterdam, Netherlands; London, United Kingdom; Remote - Europe; Remote - United States

Status

Open

Posted

2026-06-26T10:11:07+00:00

Senior software developer on Nebius's Models Team, which brings open-source models into the Token Factory inference platform. Work covers serving large models in production: cache-aware routing, KV-cache offloading, disaggregated serving, autoscaling with fast model loading over InfiniBand, and maintaining forks of vLLM and TRT-LLM, plus tooling for benchmarking, diagnostics and rollouts. The posting asks for production LLM serving experience and strong Python or Go, with distributed systems. The eight-engineer team is remote-first and meets in person every one to two months.