Senior Applied Scientist, Efficient LLM Inference & Model Optimization

About the role

Nebius is seeking a Senior Applied Scientist to join the Token Factory team to address frontier inference bottlenecks. The role involves designing rigorous experiments, writing high-quality code, and collaborating with engineers to transition research into production-ready inference capabilities.

Responsibilities

• Own focused research projects from hypothesis through experiment, ablation, prototype, and production handoff.
• Prepare internal reports, technical blogs, or papers when the work is externally credible.
• Partner directly with MLEs to ensure research prototypes become usable production components.
• Define and execute research programs in efficient LLM and VLM inference with measurable production impact.
• Invent, evaluate, and productionize methods for quantization, QAT, distillation, speculative decoding, KV-cache reuse, KV-cache compression, long-context inference, MoE routing, and model/runtime co-optimization.
• Build high-quality prototypes in PyTorch, Triton, CUDA-adjacent tooling, or inference-serving frameworks.
• Design rigorous evaluation methodology covering quality, latency, throughput, numerical stability, memory footprint, tail latency, and cost per token.
• Mentor engineers and scientists on experimental design, scientific rigor, and model/system tradeoffs.

Required skills

• Machine Learning
• LLM
• VLM
• Transformer inference
• Model compression
• Quantization
• Distillation
• Python
• PyTorch
• Experimental design

Nice to have

• vLLM
• SGLang
• TensorRT-LLM
• NVIDIA Dynamo
• FlashAttention
• FlashInfer
• Triton
• CUDA
• SFT
• DPO

Qualifications

• PhD in computer science, machine learning, ML systems, computer systems, computer architecture, electrical engineering, applied math, or a closely related field.

Benefits

• Competitive compensation
• Career growth and learning opportunities
• Flexibility and ownership
• Collaborative and innovative culture

About the Company

Nebius is building a full-stack AI cloud platform that supports developers and enterprises from data and model training through to production deployment. Listed on Nasdaq, the company has a global footprint with R&D hubs across Europe, the UK, North America and Israel.