AI Infra Onboard Performance Intern

XPENG is a leading smart technology company at the forefront of innovation, integrating advanced AI and autonomous driving technologies into its vehicles, including electric vehicles (EVs), electric vertical take-off and landing (eVTOL) aircraft, and robotics. With a strong focus on intelligent mobility, XPENG is dedicated to reshaping the future of transportation through cutting-edge R&D in AI, machine learning, and smart connectivity.

Key Responsibilities

• Design and optimize software for deploying large-scale AI models in production vehicles.
• Profile and improve inference performance across compute, memory, and I/O systems.
• Reduce latency and improve power efficiency on embedded automotive platforms.
• Deliver production-ready optimizations that scale reliably across the vehicle fleet.

Basic Qualifications

• 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 (memory hierarchy, parallelism, vectorization, scheduling).

• Proven experience in application performance analysis and optimization, using profiling tools to diagnose and resolve bottlenecks.

Preferred Qualifications

• Experience writing and optimizing CPU or CUDA kernels.

• Experience developing performance tooling and instrumentation (e.g., eBPF, perf, custom tracing/profiling frameworks) for production or embedded systems.

• Familiarity with embedded or automotive compute platforms (e.g., NVIDIA Orin, Drive) and their power/thermal constraints.

• Previous experience in the autonomous driving or robotics industry.

• Effective at solving complex problems collaboratively within larger cross-functional teams.

What do we provide:

• A fun, supportive and engaging environment.

• Infrastructures and computational resources to support your work.

…