I will optimise and deploy ml models on edge devices

Running a machine learning model on a microcontroller or edge board is a very different challenge from cloud deployment. I specialise in neural network quantisation, pruning, and optimisation for resource-constrained hardware including NVIDIA Jetson, STM32 (ARM Cortex-M), and other embedded platforms.

I've deployed YOLO with TensorRT on Jetson for real-time inference and performed CMSIS-NN optimisations on ARM Cortex-M85. I'll make your model lean, fast, and production-ready.