Neural Network Compression Engineer

Ambarella Hsinchu, Taiwan

Semiconductor Manufacturing · 501-1,000 employees

Yesterday

Mid (2-5 yrs) Full-time Taiwan

Create a free account to apply — email only, no card. You can also save this posting or score it against your profile with AI.

Applying here? Try the free cover letter tool — paste this posting and your résumé, no account needed.

About the role

Develop and maintain neural network compression algorithms and tools for edge AI vision processors. The role focuses on optimizing models to extract valuable data from high-resolution video streams.

What they look for

Neural Network Compression Pruning Quantization Knowledge Distillation CNN Transformer Computer Vision Large Language Models Machine Learning Frameworks C C++ Python Compression Training Quantization-aware Training

Requirements

Candidates must have a strong background in neural network compression techniques such as pruning and quantization. Proficiency in C/C++ or Python and experience with computer vision frameworks are required.

Full description

AI Vision Processors For Edge Applications

Our solutions make cameras smarter by extracting valuable data from high-resolution video streams.

Job Description

Develop and maintain neural network compression algorithm and tool

Job Requirements:

1. Strong background of neural network compression knowledge, including pruning, quantization and knowledge distillation

2. Strong background of CNN/transformer-based computer vision and large language model knowledge

3. Familiar with computer vision and machine learning framework.

4. Skilled in C/C++ (and/or) Python programing

5. Compression training ((Pruning/Quantization-aware) experience is a plus