Senior LLM Inference Systems Engineer

Snowflake; Menlo Park (CA); On-site; USD 236,000 - 310,000; Full time

Benefits offered by this job

Medical insurance

Bonus & equity plan

401(k) retirement plan

12 paid holidays

Job summary

Snowflake is seeking talented systems developers and researchers to join the AI Research team in Menlo Park. You will advance the state of the art in LLM inference systems and optimization, spanning distributed serving, runtime systems, and GPU kernels.

The role focuses on building high-performance, adaptive inference platforms that scale with evolving models and hardware, while collaborating with model researchers and product teams to deploy innovations in production.

Qualifications

• 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 for large-scale models.
• Hands-on experience with LLM inference and serving frameworks such as vLLM, SGLang, or TensorRT-LLM.

Responsibilities

• Design and develop high-performance LLM inference systems across distributed serving, runtime systems, GPU execution, and kernels.
• Develop techniques to reduce latency and increase throughput and memory efficiency.
• Explore adaptive parallelism, speculative decoding, disaggregated inference, scheduling and batching, and KV-cache optimization.

Skills

LLM inference systems

Distributed AI systems

GPU systems

High-performance computing

Education

Bachelor's degree in CS/EE or related field

Master's degree or PhD preferred

Tools

vLLM

SGLang

TensorRT-LLM

Job description

Snowflake is seeking talented systems developers and researchers to join the AI Research team in Menlo Park. You will advance the state of the art in LLM inference systems and optimization, spanning distributed serving, runtime systems, and GPU kernels.

The role focuses on building high-performance, adaptive inference platforms that scale with evolving models and hardware, while collaborating with model researchers and product teams to deploy innovations in production.