GPU-Optimized LLM Inference Engineer

Intel Corporation; Folsom (CA); Hybrid; USD 171,000 - 315,000; Full time

Job summary

Intel Corporation is seeking a performance-obsessed AI Infrastructure Engineer to push LLM inference to the absolute limits on Intel GPUs, profiling bottlenecks and coding high-performance kernels across the stack.

You will upstream improvements to vLLM, SGLang and PyTorch, collaborate with architecture and compiler teams to shape future GPU roadmaps, and drive performance in state-of-the-art generative AI workloads.

Qualifications

• Bachelors degree with 4+ years in GPU computing or AI systems
• Masters degree with 3+ years experience OR PhD
• Proficient in modern C++ and Python

Responsibilities

• Own end-to-end optimization pipeline for running LLMs on Intel GPUs.
• Profile bottlenecks and diagnose cross-stack performance issues.
• Develop and optimize custom GPU kernels for attention, MoE, quantization.
• Upstream improvements to vLLM, SGLang, and PyTorch.
• Collaborate with architecture and compiler teams to shape GPU roadmaps.
• Contribute to AI infrastructure performance initiatives.

Skills

C++

Python

GPU computing

Education

Bachelor's degree in CS/SE/AI

Master's degree

PhD

Tools

Triton

SYCL

CUDA/CUTLASS

vLLM

SGLang

PyTorch

Job description

Intel Corporation is seeking a performance-obsessed AI Infrastructure Engineer to push LLM inference to the absolute limits on Intel GPUs, profiling bottlenecks and coding high-performance kernels across the stack.

You will upstream improvements to vLLM, SGLang and PyTorch, collaborate with architecture and compiler teams to shape future GPU roadmaps, and drive performance in state-of-the-art generative AI workloads.