Data Science Intern- Model Optimization
About The Position
Quadric is redefining edge AI with the industry's first General Purpose Neural Processing Unit (GPNPU), enabling developers to run both neural network inference and conventional C++ code on a single programmable architecture. Our technology powers intelligent edge devices across automotive, industrial, robotics, and embedded systems. 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. You will join the data science team for an internship focused on model optimization for Quadric's custom GPNPU architecture. Working alongside a senior data scientist mentor, you will contribute to the quantization library and/or numerical accuracy testing and debugging infrastructure. Note: Our preference is for this internship to be based out of our Burlingame, California office. Candidates should be based in the Bay Area or able to relocate for the internship period and available to work on site.
Requirements
- Currently pursuing or recently graduated with a B.S., M.S., or Ph.D. in CS, EE, Applied Math, or a related field.
- Solid Python skills and comfort with PyTorch (or TensorFlow), NumPy, and basic data-viz tools (Matplotlib/Plotly).
- Coursework or project experience in machine learning; familiarity with CNNs and/or Transformers.
- Curiosity about quantization, numerical representation, fixed-point arithmetic, or low-level performance.
- Ability to read a research paper and discuss the core ideas.
Nice To Haves
- Prior exposure to quantization, model compression, or any of PyTorch FX/PTQ/QAT, TF-Lite, ONNX-Runtime, TVM, or MLIR Quant.
- Any hands-on experience with embedded systems, DSPs, GPUs, or other accelerators.
Responsibilities
- Run and contribute to new quantization workflows on vision and language models under mentor guidance.
- Build calibration datasets and tooling to visualize per-layer error and distribution statistics for debugging.
- Contribute to numerical accuracy testing infrastructure, numerical validation debug tooling of neural networks, and the quantization library.
Benefits
- Catered lunch each day in our office
- Downtown Burlingame office location, close to shops, cafes, and local amenities
- A work culture focused on innovative disruption
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Career Level
Intern
Education Level
No Education Listed
