Overview In this role you will design, develop, and maintain new functionality in oneDNN to accelerate AI workloads on Intel CPUs and GPUs. You will collaborate with cross-functional teams to support AI frameworks and the broader oneDNN ecosystem. The role focuses on performance-critical components and optimization, contributing to open-source software. This is a chance to help drive Intel's AI strategy through scalable, high-performance software.
Compensation / Benefits- competitive pay
- stock bonuses
- health benefits
- retirement
- vacation
Responsibilities- Design, develop, and maintain new oneDNN functionality for AI workloads
- Optimize performance of AI workloads on Intel CPUs/GPUs
- Support developers optimizing AI frameworks and workloads in a cross-platform ecosystem
- Contribute to open-source software and and collaborate with other contributors
- Work with Linux-based development and low-level optimizations on accelerators
Key requirements- C and C++ programming experience
- Maintaining or contributing to open-source software projects
- Software libraries design and architecture
- Implementation of linear algebra algorithms (BLAS, LAPACK, or PyTorch)
- Performance engineering and software performance optimizations
- Floating point arithmetic and numerical stability
- Software development on Linux
- Low-level performance optimizations using CUDA, x86 assembly or intrinsics, or OpenCL
- C and C++
- open-source contributions
- software libraries design and architecture
- linear algebra algorithms (BLAS, LAPACK, or PyTorch)
- performance engineering and optimizations
- floating point arithmetic and numerical stability
