XPENG Motors
AI Infra Onboard Performance Intern
Santa Clara, CA +1 · Internship · Posted Jun 5, 2026
- Location
- Santa Clara, CA
Mountain View, California, United States - Education
- Master's or PhD in CS/CE/EE or equivalent
About the job
Optimize software and inference performance for deploying large-scale AI models on production vehicle platforms.
What you'll do
- Design and optimize software for production deployment of large-scale AI models.
- Profile and improve inference performance across compute, memory, and I/O systems.
- Reduce latency and power use on embedded automotive platforms and deliver scalable production optimizations.
What they ask for
- Master's or PhD in CS/CE/EE or equivalent, with relevant industry or research experience.
- Strong expertise in C++ and Python, including performance-sensitive, production-quality code.
- In-depth understanding of computer architecture and high-performance computing, including memory hierarchy, parallelism, vectorization, and scheduling.
- Proven experience analyzing and optimizing application performance with profiling tools.
Nice to have
- Experience writing and optimizing CPU or CUDA kernels; developing performance tooling or instrumentation such as eBPF, perf, or custom tracing/profiling frameworks.
- Familiarity with embedded or automotive compute platforms such as NVIDIA Orin or Drive, or experience in autonomous driving or robotics.
Tools
C++, Python, CUDA, eBPF, perf, NVIDIA Orin, Drive
AI focus
Deploy and optimize large-scale AI models for production vehicles, including inference performance on embedded automotive platforms.
Model-written summary · the original posting is authoritative