Deep Learning Compiler Intern

Job Title

Deep Learning Compiler Intern

Role Summary

Work with senior compiler engineers on CGC, Quadric’s neural network compiler that lowers models to code for the Chimera GPNPU. This is a hands-on internship focused on implementing and debugging compiler passes, IR transformations, and hardware-aware code generation that flow end-to-end into C++ running on Quadric silicon.

Preference for candidates who can be based in the Burlingame, CA office and available to work on site for the internship period.

Experience Level

Internship / Entry-level. Intended for students currently enrolled in an undergraduate or graduate degree program; no prior years-of-experience requirement specified.

Responsibilities

Primary responsibilities include extending the CGC compiler pipeline, diagnosing compilation issues, and improving performance mapping of neural networks to hardware.

• Build and extend compiler passes that lower neural network IR to GPNPU-targeted code.
• Trace and diagnose compilation failures by following generated C++ back through the pipeline; use IR dumps and static analysis.
• Work on compiler decisions and optimizations to reduce data movement and increase core utilization.
• Collaborate with kernel, hardware, and data science teams to align compiler features with model and hardware constraints.
• Contribute to test infrastructure, debugging utilities, and developer ergonomics across the compiler and runtime.

Requirements

Must-have technical skills and capabilities for successful performance in the role.

• Strong proficiency in Python and C++.
• Foundational understanding of compiler concepts: intermediate representations, dataflow analysis, and transformation passes.
• Comfort reading and reasoning about large, unfamiliar codebases.
• Demonstrated problem-solving, debugging skills, and clear technical communication.

Preferred qualifications:

• Coursework or project experience with compilers, program analysis, or domain-specific languages.
• Exposure to ML compiler frameworks such as TVM, MLIR, XLA, Glow, or IREE.
• Familiarity with neural network quantization, fixed-point arithmetic, or numerical analysis.
• Experience with hardware-aware code generation for accelerators and some exposure to assembly or low-level code generation.
• Previous internship experience in compilers, ML systems, or performance engineering.

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.