Senior AI Performance Engineer — Edge Inference Expert

Arm; San Jose (CA); Hybrid; USD 263,000 - 355,000; Full time

Job summary

Arm is seeking an engineer in San Jose to optimize AI workloads on Arm technology, delivering best-in-class inference performance for production models on edge devices. The role involves kernel-level to system-level optimization, frequent collaboration with customers across the Bay Area, and influencing tooling roadmaps with real-world insights.

Ideal candidates have deep knowledge of DNN optimization, parallel memory hierarchies, and strong Python/C++ development skills, with experience in

Qualifications

• Experience optimizing DNNs in Triton, CUDA or other kernel level programming language.
• Deep understanding of parallel computing, memory hierarchies and performance optimization techniques for DNNs.
• Strong programming skills in Python and C++, with solid experience in modern AI frameworks and execution models, plus profiling/analysis tools.
• Strong communication and interpersonal skills.

Responsibilities

• Develop highly optimized solutions for AI workloads, from kernel level to system level, to meet the needs of the customer application.
• Create production quality reference implementations, documentation, and performance focused technical content
• Act as a technical bridge between customers and internal teams, driving resolution of complex performance issues
• Influence Arm’s IP and software roadmap through insights from real-world customer use cases

Skills

DNN optimization

CUDA

Kernel programming

Python

C++

Tools

Triton

CUDA

Job description

Arm is seeking an engineer in San Jose to optimize AI workloads on Arm technology, delivering best-in-class inference performance for production models on edge devices. The role involves kernel-level to system-level optimization, frequent collaboration with customers across the Bay Area, and influencing tooling roadmaps with real-world insights.

Ideal candidates have deep knowledge of DNN optimization, parallel memory hierarchies, and strong Python/C++ development skills, with experience in