LLM Inference Performance Engineer

Intel Corporation; Hillsboro (OR); Hybrid; USD 171,000 - 315,000; Full time

Job summary

Intel in Santa Clara, CA is seeking an AI Infrastructure Engineer to push LLM inference on Intel GPUs to new performance heights. You will own end-to-end optimization, profile bottlenecks, and write high-performance kernels for attention, MoE, and quantization.

You will upstream improvements to vLLM, SGLang, and PyTorch, working across architecture, compiler teams, and open-source communities. Hybrid work model available.

Qualifications

• Bachelor's or higher in CS/SE/AI with 4+ years in relevant field.
• 3+ years GPU computing or HPC experience.
• Proficient in C++ and Python; comfortable with large-scale systems.

Responsibilities

• Own end-to-end optimization for running LLMs on Intel GPUs.
• Profile and resolve cross-stack performance bottlenecks.
• Design and optimize high-performance kernels for attention, MoE, quantization.
• Upstream improvements to vLLM, SGLang, PyTorch.
• Collaborate with architecture and compiler teams to shape GPU roadmaps.

Skills

C++

Python

GPU computing

Systems programming

Education

Bachelor's degree in CS/SE/AI

Master's degree or PhD

Tools

vLLM

SGLang

PyTorch

CUDA/CUTLASS

Triton

Job description

Intel in Santa Clara, CA is seeking an AI Infrastructure Engineer to push LLM inference on Intel GPUs to new performance heights. You will own end-to-end optimization, profile bottlenecks, and write high-performance kernels for attention, MoE, and quantization.

You will upstream improvements to vLLM, SGLang, and PyTorch, working across architecture, compiler teams, and open-source communities. Hybrid work model available.