Senior Applied Scientist, Efficient LLM Inference & Model Optimization

About the role

Nebius is seeking a scientist to lead research and optimization projects focused on LLM and VLM inference bottlenecks. You will conduct rigorous experiments, develop prototypes, and translate findings into production capabilities while investigating trade-offs across latency, throughput, and cost. The role involves collaborating with engineering teams to implement solutions and sharing research through technical artifacts and publications.

Responsibilities

• Lead research projects in efficient LLM and VLM inference, from hypotheses and experiments through ablations, prototypes, and production handoff.
• Develop and evaluate methods spanning quantization, quantization-aware training (QAT), distillation, speculative decoding, KV-cache reuse, KV-cache compression, long-context inference, MoE routing, and model/runtime co-optimization.
• Build prototypes using PyTorch, Triton, CUDA-adjacent tooling, or inference-serving frameworks, and collaborate with MLEs and platform engineers to turn them into production components.
• Research LLM request routing and scheduling strategies, including cache-aware load balancing and prefill–decode disaggregation (PDD).
• Investigate multi-node inference for dense and mixture-of-experts models, including wide expert parallelism (WideEP).
• Develop rigorous evaluations covering quality, latency, throughput, numerical stability, memory footprint, tail latency, and cost per token.
• Work with MLE, GPU kernel, backend infrastructure, product, and customer teams to select research priorities with measurable production impact.
• Share results through internal reports, technical blogs, papers, and open-source artifacts, and mentor engineers and scientists on experimental design, scientific rigor, and model/system trade-offs.

Required skills

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

Nice to have

• vLLM
• SGLang
• TensorRT-LLM
• FlashAttention
• FlashInfer
• Triton
• CUDA
• Distributed inference
• SFT
• DPO

Qualifications

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

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 and headquartered in Amsterdam, the company has a global footprint with R&D hubs across Europe, the UK, North America and Israel.