Senior/Staff System Research Engineer - LLM Inference Optimization at Snowflake · Bellevue, WA · Joined
S
Senior/Staff System Research Engineer - LLM Inference Optimization
Snowflake · Bellevue, WA · Just now · 0 applicants
NewHybridFull-timeLead
Pay
$236k–$330kListed
Workplace
Hybrid
Job type
Full-time
Level
Lead
Source: jobright · Posted by joined-scrapper
About the role
Snowflake is seeking a Senior/Staff System Research Engineer to advance LLM inference systems and optimization across distributed serving, runtime systems, GPU kernels, and model-system co-design, taking innovations from research to production.
What you’ll do
Advance LLM inference systems and optimization
Drive innovations from research to production
What you’ll need
Bachelor's degree in Computer Science, Electrical Engineering, or related field
5+ years of experience in LLM inference, distributed AI, GPU systems, or HPC
Hands-on experience with vLLM, SGLang, TensorRT-LLM or similar
Experience with CUDA, Triton, or similar GPU programming
Experience with performance libraries like CUTLASS, cuBLAS, cuDNN
Strong communication and collaboration skills
Original job description
Snowflake is powering the era of the agentic enterprise and building the next generation of high-performance, intelligent AI systems. The Senior/Staff System Research Engineer will advance LLM inference systems and optimization across distributed serving, runtime systems, GPU kernels, and model-system co-design, taking innovations from research through…