Senior GPU Performance Engineer: Low-Level AI Kernels

Intel; Hillsboro (OR); Hybrid; USD 195,000 - 276,000; Full time

Benefits offered by this job

Stock bonuses

Health insurance

Retirement plan

Vacation

Job summary

Intel's Software and AI (SAI) organization seeks a high-caliber software engineer to contribute to oneDNN development and low-level optimization on Intel hardware. You will focus on creating optimized math primitives, GPU kernels, and JIT/codegen infrastructure for AI workloads such as OpenVINO, TensorFlow, PyTorch, and ONNX Runtime.

The role emphasizes low-level engineering rather than ML model development, with opportunities to work on performance modeling, validation, and collaboration with

Qualifications

• Education: BSc/MSc/PhD in Computer Science, Computer Engineering, Mathematics or physics or related field.
• 5+ years of professional software development experience with expert-level modern C++.
• 2+ years of GPU kernel optimization via SYCL/DPC++, OpenCL, CUDA, or HIP or 5+ years CPU optimization experience.
• Strong foundations in computer architecture, caches, memory subsystems, and parallel programming.

Responsibilities

• Develop high-performance GEMM, convolution, and attention kernels for AI workloads.
• Design scalable JIT and codegen infrastructure for GPU kernel generation.
• Implement fusion and memory-traffic optimizations to maximize hardware utilization.
• Profile and eliminate performance bottlenecks across oneDNN GPU primitives and runtime paths.
• Co-design GPU primitives and kernel architectures for next-generation Intel GPUs.
• Improve validation, benchmarking, and CI infrastructure for performance-critical GPU workloads.

Skills

C++

GPU kernels

Parallel programming

Performance optimization

Education

BSc / MSc / PhD in CS/CE/Math/Physics

Tools

SYCL/DPC++

OpenCL

CUDA

HIP

Job description

Intel's Software and AI (SAI) organization seeks a high-caliber software engineer to contribute to oneDNN development and low-level optimization on Intel hardware. You will focus on creating optimized math primitives, GPU kernels, and JIT/codegen infrastructure for AI workloads such as OpenVINO, TensorFlow, PyTorch, and ONNX Runtime.

The role emphasizes low-level engineering rather than ML model development, with opportunities to work on performance modeling, validation, and collaboration with