Deep Learning Researcher Intern - Model Quantization
Core
Develop and implement low-bit and mixed-precision quantization algorithms to improve the efficiency and performance of deep learning models for STMicroelectronics chips.
Role type
Research intern (model quantization)
Builds
Quantized deep learning models for semiconductor inference
Domain
Semiconductor / Deep Learning / Model Compression
Deliverable
production ML models
Required skills
Deep learning frameworks (TensorFlow, PyTorch), Model quantization (QAT, PTQ), Python, Neural network architectures
Preferred skills
C++, Generative AI for quantization
Responsibilities
Develop low-bit quantization techniques, Analyze model performance trade-offs, R&D on mixed-precision quantization, Document methodologies and results
