Tasks:
- * Apply quantization and model compression
- * Convert models and adapt operators
- * Deploy and productionize on-device deep learning models
- * Develop and maintain training and deployment toolchains
- * Optimize edge inference performance and memory usage
- * Profile performance and troubleshoot deployment issues
Perks/Benefits:
- + Opportunity for full-time conversion after internship
- + Systematic training
Skills/Tech stack required:
[ARM] [C#] [C++] [CNN] [Deep learning] [DSP] [Inference Optimization] [Knowledge Distillation] [Linux] [Low-bit quantization] [MNN] [Model Conversion] [Model Optimization] [Model Quantization] [NPU] [Operator performance profiling] [Performance Profiling] [Pruning] [PTQ] [Python] [PyTorch] [QAT] [QNN] [TensorFlow Lite] [TensorRT] [Transformer]
Educational requirements:
[Master's Degree] [PhD]
Role(s):
[AI Engineer] [Deep Learning Engineer] [Edge AI Engineer] [Engineer] [Learning Engineer] [Machine Learning Engineer]