Senior/Staff System Research Engineer – LLM Inference Optimization

The role

This person will design and develop high-performance LLM inference systems. They will work on the full inference stack including distributed serving, runtime systems, GPU kernels, and model-system co-design.

What you will do

• Design and develop high-performance LLM inference systems.
• Develop novel techniques to improve inference latency, speed, throughput, memory efficiency, scalability, and cost.
• Explore advanced inference techniques like speculative decoding and KV-cache management.
• Develop adaptive and intelligent inference systems that automatically optimize execution.
• Apply AI-driven and AI-native approaches to systems engineering.
• Identify high-impact performance and systems problems and drive solutions from research to production.
• Design distributed inference strategies across GPUs and nodes.
• Develop efficient approaches for multi-model serving and dynamic resource management.
• Analyze and optimize GPU kernels and operators.
• Profile and benchmark end-to-end workloads to identify bottlenecks.

Required qualifications

• Bachelor’s degree in Computer Science, Electrical Engineering, or a related field.
• 5+ years of experience in LLM inference systems, distributed AI systems, GPU systems, or high-performance computing.
• Strong understanding of modern LLM inference architectures and performance tradeoffs.
• Hands-on experience with modern LLM inference and serving frameworks, such as vLLM, SGLang, TensorRT-LLM, or similar systems.
• Experience designing, extending, or optimizing inference runtimes.
• Strong understanding of GPU architectures and experience with CUDA, Triton, or similar GPU programming environments.
• Experience with performance-oriented libraries and frameworks such as CUTLASS, cuBLAS, cuDNN, or related technologies.
• Experience profiling and diagnosing end-to-end system performance using Nsight Systems, Nsight Compute, or equivalent tools.
• Demonstrated ability to operate as an independent problem identifier and solver.
• Strong ability to work across model, runtime, distributed system, and hardware layers.
• Excellent communication skills and the ability to collaborate effectively across teams.

Nice to have

• Master’s degree or PhD
• Experience using AI-native engineering approaches to accelerate software development, experimentation, debugging, optimization, or system adaptation

About the company

Snowflake is powering the era of the agentic enterprise. The company is growing fast and scaling its team to enable and accelerate growth.