Edge AI Data Science Intern: Quantization & Debugging

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

Benefits offered by this job

Catered lunch

Downtown Burlingame

Innovative disruption

Job summary

Quadric in Burlingame, CA, is seeking an intern for the data science team to work on model optimization for its GPNPU architecture. You will contribute to the quantization library and to numerical accuracy testing under a senior mentor, with on-site work preferred.

As part of the internship you will build calibration data, tooling to visualize per-layer statistics, and help validate neural networks for vision and language models.

Qualifications

• 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.

Responsibilities

• Run and contribute to quantization workflows on vision and language models.
• Build calibration datasets and tooling to visualize per-layer error and distribution statistics for debugging.
• Contribute to numerical accuracy testing infrastructure and the quantization library.

Skills

Python

PyTorch

NumPy

Data Viz

Education

CS/EE/Applied Math degree

Tools

PyTorch

TensorFlow

Matplotlib/Plotly

Job description

Quadric in Burlingame, CA, is seeking an intern for the data science team to work on model optimization for its GPNPU architecture. You will contribute to the quantization library and to numerical accuracy testing under a senior mentor, with on-site work preferred.

As part of the internship you will build calibration data, tooling to visualize per-layer statistics, and help validate neural networks for vision and language models.