jobs

Senior ML 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

In inglese

Company

Nebius

Location

Amsterdam, Netherlands; Berlin, Germany; Israel; London, United Kingdom; Prague, Czech Republic; Remote - Europe

Status

Open

Posted

2026-02-25T11:51:18+00:00

Nebius is hiring a senior machine learning engineer for Token Factory, the inference and fine-tuning platform inside its GPU cloud. The work centres on LLM inference optimisation: profiling GPU workloads, implementing speculative decoding, supporting open-source inference engines, and productionising low-precision (FP8, NVFP4/MXFP4) training and inference. The posting asks for deep knowledge of transformer architecture and GPU memory tradeoffs, strong Python and deep-learning framework experience, profiling with Nsight or PyTorch profiler, and CI/CD and testing habits. Distributed-systems and kernel-language experience is listed as a plus.