Job Description

Quadric has created an innovative general purpose neural processing unit (GPNPU) architecture. Quadric's co-optimized software and hardware is targeted to run neural network (NN) inference workloads in a wide variety of edge and endpoint devices, ranging from battery operated smart-sensor systems to high-performance automotive or autonomous vehicle systems. Unlike other NPUs or neural network accelerators in the industry today that can only accelerate a portion of a machine learning graph, the Quadric GPNPU executes both NN graph code and conventional C++ DSP and control code.

The Role

As a Software Engineer Intern - Compiler, you will work closely with our senior compiler engineers on CGC, Quadric's neural network compiler that lowers to code targeting the Chimera GPNPU. You will dig into real compiler passes — layout selection, memory allocation, operator splitting, code generation — and see your changes flow end-to-end into the C++ that runs on Quadric silicon. This is a hands-on role where you will gain experience designing IR transformations, debugging generated code, and improving how efficiently neural networks map to hardware.

Note: Our preference is for a candidate willing to relocate to the California Bay Area who can regularly collaborate from our Burlingame office.

Responsibilities

• Develop & Implement: Help 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. Use IR dumps and static analyses to investigate compilation failures and performance regressions.
• Code Optimization: Work alongside senior engineers to improve compiler decisions to reduce data movement and increase core utilization. -
• Collaborate: Partner with the kernel, hardware, and data science teams to align compiler features with real model requirements and hardware constraints.
• Toolchain Contribution: Contribute to test infrastructure, debugging utilities, and developer ergonomics across the CGC pipeline and runtime.

Requirements

Must-Haves:

• 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: intermediate representations, dataflow analysis, and transformation passes.
• Comfort reading and reasoning about large, unfamiliar codebases.
• Demonstrated capability in problem-solving, debugging, and clear technical communication.

Nice-to-Haves (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 (GPU, DSP, NPU).
• Some exposure to assembly or low-level code generation.
• Previous internship experience in compilers, ML systems, or performance engineering.

Benefits

At Quadric, we value Integrity, Humility, and Happiness. What we expect from one another is simple and clear: Initiative, Collaboration, and Completion. We are a collaborative team focused on building something extraordinary in the edge computing space. 

Founded in 2016 and based in downtown Burlingame, California, Quadric is building the world’s first supercomputer designed for the real-time needs of edge devices. Quadric aims to empower developers in every industry with superpowers to create tomorrow’s technology, today. The company was co-founded by technologists from MIT and Carnegie Mellon, who were previously the technical co-founders of the Bitcoin computing company 21.

Job Tags

Similar Jobs