AI Kernel Engineer Intern

Job Title

AI Kernel Engineer Intern

Role Summary

Work with senior AI kernel engineers to enable AI/LLM models to run efficiently on the Quadric GPNPU platform. The role focuses on developing, profiling, and optimizing kernel and operator code to improve inference performance and the associated toolchain.

This is a hands-on internship intended to build practical skills in hardware-aware optimization and performance profiling. Preference for on-site placement in Burlingame, California.

Experience Level

Entry-level internship. Suitable for current undergraduate or graduate students; no specific years of professional experience required.

Responsibilities

Core responsibilities include:

• Implement and optimize AI/LLM kernels and operators for the Quadric platform.
• Profile kernel performance to identify compute, data, and parallelism bottlenecks.
• Optimize C/C++ code to maximize hardware utilization across workloads.
• Collaborate with compiler, runtime, and systems teams across the AI inference stack.
• Contribute to improvements in the Quadric toolchain, compiler, and runtime.

Requirements

Must-have technical skills and attributes:

• Strong proficiency in C/C++ and Python.
• Foundational understanding of computer architecture and hardware-software interaction.
• Demonstrated problem-solving, debugging, and clear technical communication skills.
• Ability to work on-site in Burlingame, CA for the internship period (preference).

Nice-to-have:

• Experience profiling model or kernel inference performance.
• Exposure to CUDA, DSP, NEON, Triton, or similar compute development frameworks.
• Familiarity with assembly language.
• Previous internship experience in hardware-oriented software or AI/ML optimization.

Education Requirements

Currently pursuing a Bachelor's, Master's, or PhD in Computer Science, Electrical Engineering, or a related field.

About the Company

Company: Quadric

Headquarters: Burlingame, California, United States

Quadric is building the world’s first supercomputer designed for the real-time needs of edge devices. Founded in 2016, the company empowers developers across industries with innovative general-purpose neural processing unit (GPNPU) architecture for neural network workloads. Co-founded by technologists from MIT and Carnegie Mellon, Quadric aims to enable groundbreaking technology development.