About the role#
As an AI Infra Onboard Performance Intern, you will work on software for deploying large-scale AI models in production vehicles. You will focus on profiling and improving inference performance across compute, memory, and I/O systems. Your goal is to reduce latency and improve power efficiency on embedded automotive platforms while delivering optimizations that scale across the vehicle fleet.
What you'll do#
- Design and optimize software for deploying large-scale AI models.
- Profile and improve inference performance.
- Reduce latency and improve power efficiency on embedded automotive platforms.
- Deliver production-ready optimizations.
- Collaborate within larger cross-functional teams.
What you'll need#
- Master's or PhD in Computer Science, Computer Engineering, Electrical Engineering, or an equivalent field.
- Strong expertise in C++ and Python.
- In-depth understanding of computer architecture and high-performance computing.
- Proven experience in application performance analysis and optimization.
- Experience writing and optimizing CPU or CUDA kernels.
- Familiarity with embedded or automotive compute platforms, such as NVIDIA Orin or Drive.
- Experience developing performance tooling and instrumentation for production or embedded systems.
Location & details#
- Location: Santa Clara, California.
- Modality: On-site.
- Employment type: Full-time.
- Term: Rolling.
- Compensation: Paid internship.
About XPENG
XPENG is a Chinese manufacturer of electric vehicles founded in 2014. The company focuses on the development of smart vehicle technology, including driver-assistance systems and in-car operating software. It maintains headquarters in Guangzhou and operates additional offices in Beijing and Palo Alto. The company produces vehicles at manufacturing plants located in Guangdong province.
How to get in at XPENG
Applying early gives you a distinct advantage at XPENG, as recruiters often review the first wave of candidates before the applicant pool becomes unmanageable. Intern Insider sends an instant alert the moment a role matching your target is published anywhere, ensuring you can submit your materials among the first. Getting your application in early is a practical way to ensure your profile is seen before the pile grows. You can also improve your response rates by reaching out to the recruiters behind these roles directly to ask about the position or a potential referral. Intern Insider surfaces the specific recruiters managing XPENG roles so you can bypass the general queue and connect with the right people. This direct approach often yields better results than relying solely on automated systems.
