jobs

System Engineer (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

Company

Nebius

Location

Remote; Remote - Europe

Status

Open

Posted

2026-01-13T12:06:54+00:00

Nebius is hiring a systems engineer for Token Factory, the inference part of its GPU cloud. The job is low-level: writing and tuning kernels and runtime components for AI inference, improving inference engine performance on GPUs, profiling hardware-level bottlenecks, and adding support for new architectures such as Hopper, Blackwell and Rubin. It asks for C++ or GPU programming depth, systems-level experience with drivers or OS internals, and profiling skills. Preferred tools include CUDA, Triton, TensorRT and vLLM. Coding interviews are part of the process.