Senior AI Performance Library Architect

Intel Corporation; Hillsboro (OR); Hybrid; USD 171,000 - 315,000; Full time

Job summary

Intel Corporation’s Software and AI (SAI) organization seeks a Software Development Engineer to advance oneDNN, a cross-platform open-source project powering OpenVINO, TensorFlow, PyTorch, and ONNX Runtime. You will design, develop, and maintain new functionality to accelerate AI workloads on Intel CPUs and GPUs.

You will collaborate with developers to optimize performance, contribute to a key component of Intel's AI strategy, and operate within a hybrid work model in Hillsboro, Oregon, with

Qualifications

• Master’s or PhD in Mathematics, Physics, Computer Science, or a relevant STEM field.
• 5+ years of experience in C and C++, maintaining or contributing to open-source software projects, software libraries design/architecture.
• Experience with linear algebra implementations (BLAS/LAPACK), performance engineering, and low-level optimization (CUDA/OpenCL/x86 intrinsics).

Responsibilities

• Design, develop, and maintain new functionality in oneDNN to enable performance-critical AI workloads.
• Support software developers optimizing AI frameworks and workloads for Intel CPUs and GPUs.
• Collaborate across teams to enhance cross-platform AI software for the Intel ecosystem.

Skills

C and C++

Open-source software

Software libraries design

Linear algebra algorithms

Performance engineering

Linux development

CUDA/OpenCL/x86 intrinsics

Education

Master’s or PhD in Mathematics/Physics/CS or related STEM field

Tools

CUDA

OpenCL

x86 assembly/intrinsics

Linux

Job description

Intel Corporation’s Software and AI (SAI) organization seeks a Software Development Engineer to advance oneDNN, a cross-platform open-source project powering OpenVINO, TensorFlow, PyTorch, and ONNX Runtime. You will design, develop, and maintain new functionality to accelerate AI workloads on Intel CPUs and GPUs.

You will collaborate with developers to optimize performance, contribute to a key component of Intel's AI strategy, and operate within a hybrid work model in Hillsboro, Oregon, with