CareerPlan

AI GPU Arch Perf Analysis Intern

PRC, Beijing, CNInternship2026-11-11 → 2026-11-19
On-site

Core

Analyze and optimize core GPU compute kernels for AI and numerical workloads to support hardware/software co-design and shape the performance of next-generation Intel GPU and AI accelerator platforms.

Role type

Graduate Intern, AI GPU Architecture Performance Analysis

Builds

Next generation Intel GPU and AI accelerator platforms

Domain

Semiconductor / GPU Architecture / AI Infrastructure

Deliverable

production ML models

Required skills

Python, AI fundamentals (models and algorithms), GPU architecture knowledge, parallel computing, performance profiling, memory system analysis

Preferred skills

CUDA/OpenCL/SYCL/Triton, performance optimization, compiler knowledge, cross-functional collaboration

Technologies

CUDA, OpenCL, SYCL, Triton, Python

Responsibilities

Analyze and optimize GPU compute kernels (GEMM, Attention, operator fusion); Reproduce AI inference and training workloads for IP validation; Perform GPU performance profiling to identify bottlenecks; Build performance profiles and models; Provide insights for HW/SW co-design

Seniority

Intern