Job Requirements
Design and develop AI/ML based applications with a focus on deployment on embedded hardware platforms(eg: Renesas RZ/V2H, NVIDA Jetson Etc.)Port and optimize AI models for real time performance on resource constrained embedded systemsPerform model quantization, pruning, and conversion (e.g, ONNX, TensorFT, TVM, TFLite, DRP-AI) for deploymentEnd to end AI model life cycle development including data preparation, training, validation and inference optimizationCustomize and adapt AI network architectures for specific edge AI use cases(e.g, object detection, classification, segmentation)Profile and debug model performance on target embedded boards to meet latency and throughput goals

 

Work Experience
Minimum 5 years of experience in AI/ML application development.Strong Python programming skills, including AI frameworks such as PyTorch, TensorFlow , kerasSolid experience in developing deep learning based solutions for Computer Vision and ImagingDeep understanding of DL architectures like CNN, FCN and their application to visual tasksExperience in model optimization techniques such as quantization, pruning, layer fusion and INT8 calibration for edge inference.Hands on experience in deploying AI models on embedded platformsProficiency in tools such as OpenCV, ONNX, TVM, TFLite or custom inference enginesUnderstanding of system constraints like memory compute and power on edge devices