Senior AI Systems Research Engineer - LLM Inference

Snowflake; Bellevue (WA); On-site; USD 236,000 - 310,000; Full time

Benefits offered by this job

Bonus and equity plan

Job summary

Snowflake is seeking AI-native thinkers for the AI Research team to advance LLM inference systems and optimization. You will work on high-performance, adaptive inference across distributed serving, GPU kernels, and system co-design, collaborating with researchers and product teams to push the frontier of AI systems.

The role emphasizes experimentation, production deployment, and sharing innovations through blogs and conferences, with a base salary range disclosed for U.S.

Qualifications

• Bachelor’s degree in CS, EE, or related field; advanced degrees preferred.
• 5+ years in LLM inference systems, distributed AI, GPU systems, or HPC.
• Strong understanding of modern LLM inference architectures and tradeoffs.
• Hands-on with LLM inference frameworks such as vLLM, SGLang, TensorRT-LLM.
• Experience designing or optimizing inference runtimes (scheduling, batching, KV-cache).
• Strong GPU expertise (CUDA, Triton) and performance libraries (CUTLASS, cuBLAS, cuDNN).
• Experience profiling with Nsight or equivalent, independent problem solving, cross-team collaboration.

Responsibilities

• Design and develop high-performance LLM inference systems across distributed serving and GPUs.
• Develop techniques to improve latency, throughput, memory efficiency, and cost.
• Explore adaptive parallelism, speculative decoding, disaggregation, and scheduling.
• Create adaptive inference systems for new models, hardware, and workloads.
• Apply AI-native approaches to profiling, configuration search, and performance tuning.
• Identify high-impact performance problems and drive solutions from research to production.
• Design distributed inference strategies across GPUs and nodes, including various parallelisms.
• Develop efficient multi-model serving, dynamic resource management, and model swapping.
• Analyze and optimize GPU kernels for attention, MoE, and other components.
• Explore model-system co-design for more efficient inference and performance benchmarking.
• Profile end-to-end workloads to identify bottlenecks across compute, memory, and networking.
• Collaborate with researchers, infra, and product teams to deploy innovations.
• Open-source and publish innovations via blogs and top ML/system conferences.

Skills

LLM inference systems

distributed AI systems

GPU systems

high-performance computing

Education

Bachelor's degree

Master's degree

PhD

Tools

vLLM

SGLang

TensorRT-LLM

Job description

Snowflake is seeking AI-native thinkers for the AI Research team to advance LLM inference systems and optimization. You will work on high-performance, adaptive inference across distributed serving, GPU kernels, and system co-design, collaborating with researchers and product teams to push the frontier of AI systems.

The role emphasizes experimentation, production deployment, and sharing innovations through blogs and conferences, with a base salary range disclosed for U.S.