Senior Applied Scientist, Efficient LLM Inference & Model Optimization
$195k - $262k • Remote • Palo Alto, California, United States
Posted 4d ago
Job Location
Palo Alto, California, United States
Tech Stack
Remote Work Policy
Fully remote
Categories
Applied AI Engineer
About the job
Nebius is building a full-stack AI cloud platform to support developers and enterprises in the global AI economy, from data and model training through to production deployment. The Nebius Token Factory is seeking scientists to tackle frontier LLM and VLM inference bottlenecks by turning them into research questions, conducting rigorous experiments, and translating findings into production capabilities. You will own focused research and optimization projects, write strong code, and produce prototypes, publications, and technical artifacts for engineers to build upon. Your research will cover areas like quantization, distillation, speculative decoding, KV-cache optimization, and model/runtime co-optimization, alongside inference engines and distributed inference architectures. You will evaluate trade-offs across model quality, latency, throughput, memory footprint, and cost per token, and collaborate with engineering teams to bring promising results into production.
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), evaluating their impact on latency, throughput, and serving cost.
- Investigate multi-node inference for dense and mixture-of-experts models, including wide expert parallelism (WideEP), studying expert placement, load imbalance, and computation/communication trade-offs.
- Develop rigorous evaluations covering quality, latency, throughput, numerical stability, memory footprint, tail latency, and cost per token, comparing serving architectures under consistent workload conditions and GPU budgets.
- 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.
Requirements
- PhD in computer science, machine learning, ML systems, computer systems, computer architecture, electrical engineering, applied mathematics, or a closely related discipline.
- Strong publication record or equivalent research artifacts in ML, ML systems, efficient inference, model compression, quantization, distillation, serving systems, or related areas.
- Strong Python and PyTorch implementation skills, with the ability to turn ideas into experiments and working prototypes.
- Deep knowledge of LLMs, VLMs, transformer inference, decoding algorithms, model compression, quantization, and production-serving trade-offs.
- Strong experimental design skills covering ablations, baselines, metrics, statistical reasoning, and failure analysis.
- Excellent written and verbal communication.