AI Inference Performance Engineer (GPU Kernels)

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

Benefits offered by this job

Stock bonuses

Health insurance

Retirement plan

Vacation

Job summary

Intel Corporation is seeking an AI Infrastructure Engineer to push LLM inference on Intel GPUs to new performance heights. You will profile, optimize, and implement high-performance kernels, working across the stack and upstreaming changes to vLLM, SGLang, and PyTorch.

The role blends hardware and software disciplines to accelerate state-of-the-art generative AI workloads. You will collaborate with hardware, compiler, and architecture teams to shape future GPU roadmaps using real GenAI workload

Qualifications

• Bachelor's degree in CS/SE/AI and 4+ years experience, or MS/PhD.
• 3+ years of relevant software engineering in GPU computing, AI systems, or HPC.
• Proficiency in modern C++ and Python; comfortable with complex systems-level code.

Responsibilities

• Own end-to-end optimization pipeline for running state-of-the-art LLMs on Intel GPUs.
• Profile, diagnose, and resolve cross-stack performance bottlenecks.
• Design and optimize custom high-performance kernels for attention, MoE, quantization, and fusions.
• Upstream architectural improvements to vLLM, SGLang, and PyTorch with open-source community.

Skills

C++

Python

GPU computing

HPC

Education

Bachelor’s degree in CS/SE/AI

MS/PhD in related field

Tools

vLLM

SGLang

PyTorch

CUDA/CUTLASS

Job description

Intel Corporation is seeking an AI Infrastructure Engineer to push LLM inference on Intel GPUs to new performance heights. You will profile, optimize, and implement high-performance kernels, working across the stack and upstreaming changes to vLLM, SGLang, and PyTorch.

The role blends hardware and software disciplines to accelerate state-of-the-art generative AI workloads. You will collaborate with hardware, compiler, and architecture teams to shape future GPU roadmaps using real GenAI workload