Data Science Intern - Model Optimization
QuadricJob Title
Data Science Intern - Model Optimization
Role Summary
Internship on the data science team focused on model optimization for Quadric's GPNPU architecture. The intern will work with a senior data scientist mentor to improve quantization workflows, numerical accuracy testing, and debugging tooling for vision and language models.
Preference for Bay Area candidates able to work on site in the Burlingame, CA office for the internship period.
Experience Level
Entry-level internship; suitable for current students or recent graduates. Typical candidates are pursuing or recently completed undergraduate or graduate study.
Responsibilities
Hands-on tasks and deliverables the intern will perform:
- Implement and run 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 and validation infrastructure and debug tooling for neural networks.
- Contribute code and tests to the quantization library and related model optimization tooling.
- Work closely with a mentor and the engineering team to iterate on experiments and report findings.
Requirements
Must-have technical skills and relevant experience. Preferred items are listed separately.
- Solid Python skills and familiarity with PyTorch or TensorFlow, NumPy, and data visualization 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 research papers and discuss core ideas; strong problem-solving and debugging skills.
- Comfort working on site in the Burlingame, CA office for the internship period.
Preferred
- Experience with quantization or model compression tools (PyTorch FX, PTQ/QAT, TF-Lite, ONNX Runtime, TVM, MLIR Quant).
- Hands-on experience with embedded systems, DSPs, GPUs, or other accelerators.
Education Requirements
Currently pursuing or recently graduated with a B.S., M.S., or Ph.D. in Computer Science, Electrical Engineering, Applied Mathematics, or a related technical 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.
