Hybrid GPU AI Inference Engineer

Intel Corporation; Santa Clara, Northern (CA, KY); Hybrid; USD 171,000 - 315,000; Full time

Benefits offered by this job

Stock bonuses

Health benefits

Hybrid work model

Job summary

Intel Corporation is seeking a performance-obsessed AI Infrastructure Engineer to push LLM inference on Intel GPUs. You will optimize the end-to-end stack, profile bottlenecks, and write high-performance kernels for attention, MoE, and quantization.

You will upstream improvements to vLLM, SGLang, and PyTorch, collaborating with architecture and compiler teams to shape future GPU roadmaps. This role offers hybrid work and a competitive compensation package.

Qualifications

• BS/MS/PhD in CS/SE/AI or related field required or equivalent experience.
• 3+ years in GPU computing, AI systems, or HPC.
• Proficiency in modern C++ and Python; reading and modifying complex systems.

Responsibilities

• Own end-to-end optimization for running state-of-the-art LLMs on Intel GPUs.
• Profile bottlenecks, write high-performance kernels, and integrate into frameworks.
• Upstream architectural improvements into vLLM, SGLang, PyTorch; collaborate with hardware teams.

Skills

C++ proficiency

Python proficiency

GPU computing experience

Education

Bachelor's / Master's / PhD in CS / SE / AI

Tools

Triton

SYCL

CUDA/CUTLASS

Job description

Intel Corporation is seeking a performance-obsessed AI Infrastructure Engineer to push LLM inference on Intel GPUs. You will optimize the end-to-end stack, profile bottlenecks, and write high-performance kernels for attention, MoE, and quantization.

You will upstream improvements to vLLM, SGLang, and PyTorch, collaborating with architecture and compiler teams to shape future GPU roadmaps. This role offers hybrid work and a competitive compensation package.