jobs
Staff Machine Learning Engineer, LLM Inference Optimization
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…
En inglés
- Company
- Nebius
- Location
- Amsterdam, Netherlands; Berlin, Germany; London, United Kingdom; Poland; Prague, Czech Republic; Zurich, Switzerland
- Status
- Open
- Posted
- 2026-10-21 12:25 UTC
Nebius seeks a Staff Machine Learning Engineer for its Token Factory to own production LLM and VLM inference optimization. The role covers platform-level work such as quantization, speculative decoding, KV-cache optimization, engine selection or long-context serving, plus benchmarking and deployment of engines including vLLM, SGLang and TensorRT-LLM. It asks for strong Python and PyTorch skills, hands-on transformer inference experience, and quantitative reasoning about latency, throughput, memory and cost. The posting lists several European locations and says applicants must be authorized to work in the country they apply in.
Original job posting