Edge AI Compiler Intern: Shape GPNPU Code

quadric technologies; Burlingame (CA); On-site; USD 69,000 - 79,000; Full time

Benefits offered by this job

Catered lunch

Burlingame office location

Mentorship and project ownership

Job summary

Quadric Technologies in Burlingame, CA, invites a Deep Learning Compiler Intern to work with senior compiler engineers on Quadric's CGC neural network compiler. You will design IR transformations, debug generated code, and map neural networks to the Chimera GPNPU while collaborating with kernel and hardware teams.

Ideal candidates are pursuing CS/EE degrees, proficient in Python and C++, and familiar with compiler concepts.

Qualifications

• Currently pursuing a Bachelor's, Master's, or PhD in Computer Science, Electrical Engineering, or a related field.
• Strong proficiency in Python and C++.
• Foundational understanding of compiler concepts: IRs, dataflow analysis, transformation passes.
• Comfort reading and reasoning about large, unfamiliar codebases.
• Demonstrated capability in problem‑solving, debugging, and clear technical communication.

Responsibilities

• Develop & Implement: Build and extend compiler passes that lower neural network IR to GPNPU-targeted code.
• Analyze & Debug: Diagnose compilation issues by tracing problems from generated C++ back through the pipeline.
• Code Optimization: Improve compiler decisions to reduce data movement and increase core utilization.
• Collaborate: Work with kernel, hardware, and data science teams to align features with model requirements and hardware constraints.
• Toolchain Contribution: Contribute to test infrastructure, debugging utilities, and developer ergonomics across CGC pipeline and runtime.

Skills

Python

C++

Education

Bachelor's/Master's/PhD student in CS/EE

Tools

TVM

MLIR

XLA

Glow

IREE

Job description

Quadric Technologies in Burlingame, CA, invites a Deep Learning Compiler Intern to work with senior compiler engineers on Quadric's CGC neural network compiler. You will design IR transformations, debug generated code, and map neural networks to the Chimera GPNPU while collaborating with kernel and hardware teams.

Ideal candidates are pursuing CS/EE degrees, proficient in Python and C++, and familiar with compiler concepts.