CPU Performance Developer Technology Engineer
Core
Research, design, and implement performance optimization strategies for AI, scientific, HPC, and data-intensive workloads on NVIDIA Grace/Vera CPUs.
Role type
Senior IC CPU Performance Developer
Builds
Open-source frameworks, software stacks, reference implementations, and performance libraries
Domain
High-performance computing (HPC) and CPU microarchitecture
Deliverable
production ML models
Required skills
C/C++, Python, CPU microarchitecture, performance analysis tools, optimization methodologies, algorithm design, software architecture
Preferred skills
AI/data preprocessing pipeline optimization, HPC applications, parallel computing, distributed runtime environments, SIMD instruction sets, low-level intrinsics, vectorization, open-source contributions
Technologies
NVIDIA Grace/Vera CPUs, C/C++, Python
Responsibilities
Profile and analyze CPU performance from application-level algorithms to low-level microarchitecture; collaborate with developers and researchers to resolve performance challenges; contribute to open-source frameworks and performance libraries; provide insights to shape next-generation CPU designs and compiler toolchains
Seniority
Senior, hands-on IC
