LLM Inference & Systems Optimization Engineer

Snowflake; Bellevue (KY); On-site; USD 180,000 - 240,000; Full time

Job summary

Snowflake is seeking talented systems developers and researchers to join the AI Research team and advance LLM inference systems and optimization. You will work across distributed serving, runtime systems, GPU kernels, and model-system co-design to push latency, throughput, scalability, and cost improvements.

This role emphasizes AI-native engineering and collaboration with model researchers, infrastructure, and product teams to deploy research into production.

Qualifications

• 5+ years in LLM inference systems, distributed AI, GPU systems, or HPC.
• Strong understanding of modern LLM inference architectures and tradeoffs.
• Hands-on experience with LLM inference and serving frameworks like vLLM, SGLang, TensorRT-LLM.
• Experience designing, extending, or optimizing inference runtimes (scheduling, batching, KV-cache).
• Strong understanding of GPU architectures and CUDA/Triton.
• Experience with performance libraries such as CUTLASS, cuBLAS, cuDNN.
• Experience profiling with Nsight tools.
• Independent problem solving and cross-team collaboration.
• AI-native engineering approaches to accelerate development and deployment.

Responsibilities

• Design and develop high-performance LLM inference systems across distributed serving and GPU kernels.
• Develop techniques to improve latency, generation speed, throughput, memory efficiency, scalability, and cost.
• Explore adaptive parallelism, parallel decoding, batching, and KV-cache optimization.
• Create adaptive intelligent inference systems for new model architectures and hardware.
• Apply AI-driven approaches to profiling, configuration search, and performance tuning.
• Identify bottlenecks and prototype solutions from research to production.
• Design distributed inference strategies across GPUs and nodes.
• Multi-model serving, dynamic resource management, and workload-aware scheduling.

Skills

LLM inference systems

Distributed AI systems

GPU systems

High-performance computing

Independent problem solver

Communication skills

Education

Bachelor’s in Computer Science or Electrical Engineering

Master’s degree or PhD preferred

Tools

vLLM

SGLang

TensorRT-LLM

CUDA

Triton

CUTLASS

cuBLAS

cuDNN

Nsight Systems

Nsight Compute

Job description

Snowflake is seeking talented systems developers and researchers to join the AI Research team and advance LLM inference systems and optimization. You will work across distributed serving, runtime systems, GPU kernels, and model-system co-design to push latency, throughput, scalability, and cost improvements.

This role emphasizes AI-native engineering and collaboration with model researchers, infrastructure, and product teams to deploy research into production.