Job Description

In your new role you will:

1. Develop ML application solutions across various scenarios based on the company's embedded platform

2. Work with customers to adapt their TensorFlow/PyTorch models to company's embedded platform by leveraging quantization/pruning techniques etc.

3. Assist customers in model training, optimization, and deployment on the company’s proprietary ML platform, tailored to their requirements and business data characteristics.

4. Write and maintain technical documentation, application notes

5. FAE/DFAE technical training

Your Profile

You are best equipped for this task if you have:

Education and Experience：

1. Bachelor’s degree or higher in Electronic & Information Engineering, Computer Science, Automation, Artificial Intelligence, or related technical disciplines

2. 5+ years of embedded systems development with hands-on experience in ML project lifecycle (model optimization to deployment)

Technical Skills:

1. Extensive embedded MCU development experience, familiar with MCUs and the peripherals, knowledge of mainstream embedded operating systems (e.g., FreeRTOS, Zephyr, RT-Thread)

2. In-depth understanding of machine learning and deep learning algorithm principles; proficient in mainstream ML frameworks (e.g., TensorFlow, PyTorch, Keras)

3. Experience in migrating TF/PyTorch models to ONNX/TFLM; familiar with edge optimization techniques (INT8/FP16 quantization, pruning, knowledge distillation

4. Experience at the MCU level from model development to deployment; with experience in audio/radar/image/video are preferred

Soft Skills:

1. Passionate about delving into technology, with strong problem-solving skills and a sense of responsibility

2. Excellent communication skills to effectively coordinate across departments and achieve common goals

3. Proficient in both verbal and written English communication