AI Infra Onboard Performance Intern

About the role#

This internship focuses on the design and optimization of software for deploying large-scale AI models within production vehicles. You will work on improving inference performance and reducing latency to enhance power efficiency on embedded automotive platforms.

What you'll do#

• Design and optimize software for large-scale AI model deployment.
• 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 across the vehicle fleet.
• Collaborate with cross-functional teams to solve complex technical problems.

What you'll need#

• Master's or PhD in Computer Science, Computer Engineering, Electrical Engineering, or a related field.
• Strong expertise in C++ and Python, with a focus on performance-sensitive, production-quality code.
• In-depth understanding of computer architecture and high-performance computing, including memory hierarchy, parallelism, vectorization, and scheduling.
• Proven experience in application performance analysis and optimization using profiling tools.
• Experience writing and optimizing CPU or CUDA kernels.
• Familiarity with developing performance tooling and instrumentation, such as eBPF, perf, or custom tracing frameworks.
• Knowledge of embedded or automotive compute platforms and their power or thermal constraints is preferred.
• Previous experience in the autonomous driving or robotics industry is a plus.

Location & details#

• Location: Santa Clara, California
• Work Modality: On-site
• Employment Type: Full-time
• Compensation: Paid