Description
The role focuses on compressing and deploying AI models on resource-constrained edge hardware, including NVIDIA Jetson and Raspberry Pi. Responsibilities include model quantization, pruning, architecture refinement, knowledge distillation, on-device analytics, and low-level programming for high performance and low power consumption. The posting requires a bachelor's degree in a relevant field, proficiency in Python and C/C++, familiarity with TensorFlow Lite, PyTorch, ONNX, or Edge Impulse, experience with microcontrollers, DSPs, and AI accelerators, and good English skills.
