quadric, Inc
edge computing
DataScienceIntern-ModelOptimization
Neural analysis suggests this role is
optimal for Entry candidates.
“Data Science Intern - Model Optimization at quadric, Inc. Skills: model optimization, quantization, neural networks, Python, PyTorch, TensorFlow. Run and contribute to new quantization workflows on vision and language models. Build calibration datasets and tooling to visualize per-layer error and distribution statistics for debugging”
Industry & Context.
debugging infrastructure; visualize per-layer error and distribution statistics for debugging; numerical validation debug tooling
What They're Looking For.
Must Have
Solid Python skills, comfort with PyTorch (or TensorFlow), NumPy, basic data-viz tools (Matplotlib/Plotly), Coursework or project experience in machine 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 Have
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
What You'll Do.
Run and contribute to new 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
numerical validation debug tooling of neural networks
and quantization library
How You'll Work.
Team & Collaboration
Working alongside a senior data scientist mentor; collaborative team
Communication Scope
Ability to read a research paper and discuss the core ideas
Full 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. ** Role: ** You will join the data science team for internship focused on model optimization for Quadric's custom GPNPU architecture. Working alongside a senior data scientist mentor, you will contribute to quantization library and/or numerical accuracy testing/debugging infrastructure. **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 quantization library. **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. * Bonus: prior exposure to quantization, model compression, or any of PyTorch FX/PTQ/QAT, TF-Lite, ONNX-Runtime, TVM, or MLIR Quant. * Bonus: any hands-on experience with embedded systems, DSPs, GPUs, or other accelerators. **Ben
Applying for this Data Science Intern - Model Optimization role?
Most applicants get filtered before a human reads their resume. See if yours makes the cut.
ANONYMOUS · UNFILTERED
What do employees actually say about quadric, Inc?
Real rants from real employees. Read before you apply.