Skip to content
AI.info

jobs

Senior Applied Scientist, Efficient LLM Inference & Model 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…

Company
Nebius
Location
Berlin, Germany
Status
Open
Posted
2026-10-12 11:50 UTC

Senior applied scientist position at Nebius Token Factory in Berlin, on-site. The scientist leads research projects on efficient inference for large language and vision-language models, covering quantization, distillation, speculative decoding, KV-cache reuse and compression, mixture-of-experts routing, request scheduling, prefill–decode disaggregation, and multi-node serving. Work includes PyTorch/Triton prototypes, evaluations of latency, throughput, memory, stability and cost per token, and handoff to engineering teams. The posting asks for a PhD, publication record, strong Python/PyTorch skills, and experimental design experience; it emphasizes production impact and public technical artifacts.

Original job posting