Applied Scientist

The role Nebius Token Factory needs scientists who can turn frontier inference bottlenecks into research problems, publish credible work, and then help ship the results into production. A Senior Applied Scientist owns well-scoped research and production optimization projects. They can publish or prepare high-quality technical work while also producing code, experiments, and prototypes that engineers can use. Your responsibilities include owning focused research projects from hypothesis through experiment, ablation, prototype, and production handoff; preparing internal reports, technical blogs, or papers; partnering with MLEs to ensure research prototypes become usable production components; defining and executing research programs in efficient LLM and VLM inference; inventing, evaluating, and productionizing methods for quantization, QAT, distillation, speculative decoding, KV-cache reuse, KV-cache compression, long-context inference, MoE routing, and model/runtime co-optimization; building high-quality prototypes in PyTorch, Triton, CUDA-adjacent tooling, or inference-serving frameworks; designing rigorous evaluation methodology; publishing papers, technical reports, blog posts, and open-source artifacts; collaborating with MLE, GPU kernel, backend infrastructure, product, and customer teams; mentoring engineers and scientists. Must-haves: PhD in CS/ML systems or related field; strong publication record; strong Python and PyTorch; deep understanding of LLMs, VLMs, transformer inference, decoding, quantization, production-serving tradeoffs; strong experimental design; excellent communication. Nice-to-haves: author publications in top ML venues; production deployment experience; experience with vLLM, SGLang, TensorRT-LLM, NVIDIA Dynamo, FlashAttention, Triton, CUDA; open-source artifacts; etc. Key employee benefits in the US: health insurance, 401(k), parental leave, remote work reimbursement, disability & life insurance. Pay: Base $195,200 - $262,200 USD. We note equal opportunity; eligible to work in the US.