Senior LLM Inference Systems Engineer

Aimlroles; Bellevue (WA); On-site; USD 180,000 - 270,000; Full time

Job summary

Snowflake is building the next generation of AI-native inference systems. We seek experienced researchers and systems developers to advance LLM inference, optimization, and platform-wide performance across GPUs, CPUs, and distributed runtimes.

You will collaborate with model researchers and infrastructure teams to push latency, throughput, and cost efficiency while enabling production-scale experiments and deployments.

Qualifications

• Bachelor's degree in Computer Science, Electrical Engineering, or related field; Master’s/PhD preferred.
• 5+ years in LLM inference systems, distributed AI systems, GPU systems, or HPC.
• Strong understanding of modern LLM inference architectures and tradeoffs.
• Hands-on experience with LLM inference and serving frameworks (e.g., vLLM, TensorRT-LLM).
• Experience in scheduling, batching, KV-cache management, distributed execution, and disaggregated serving.
• Strong knowledge of CUDA, Triton, and GPU programming environments.
• Experience with Nsight tools for profiling and debugging.
• Ability to work across model, runtime, distributed system, and hardware layers.
• Experience with AI-native engineering to accelerate development and experimentation.
• Excellent communication across research, engineering, and product teams.

Responsibilities

• Design and develop high-performance LLM inference systems across distributed serving and runtime layers.
• Create techniques to reduce latency and improve throughput, memory efficiency and scalability.
• Explore adaptive and parallel inference techniques and model-system co-design.
• Develop intelligent systems that auto-optimize execution for new models and hardware.
• Collaborate with researchers, engineers, and product teams to deploy innovations in production.
• Publish innovations via technical blogs and top-tier conferences.

Skills

LLM inference systems

Distributed AI systems

GPU systems

High-performance computing

Independent problem solving

Cross-team collaboration

Education

Bachelor's degree 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 building the next generation of AI-native inference systems. We seek experienced researchers and systems developers to advance LLM inference, optimization, and platform-wide performance across GPUs, CPUs, and distributed runtimes.

You will collaborate with model researchers and infrastructure teams to push latency, throughput, and cost efficiency while enabling production-scale experiments and deployments.