Improving accuracy of a Neural Network in Federated Learning using flower framework

I'm looking for an experienced programmer to help me improve the accuracy of a Neural Network I'm developing using federated learning. The exact model architecture I am considering is a simple NN developed using PyTorch NN. For the optimization technique, I will be skipping the question altogether and focusing on the flower framework. Specifically, I need someone to help me use the flwr flower framework to optimize my neural network and ensure it meets my desired metrics. The scope of this project includes all aspects of configuring and deploying the trained model, including data pre-processing, optimization hyper-parameters tuning, computation logic and more. The successful candidate should possess extensive knowledge of federated learning and its various component frameworks. They should also be proficient in coding with various technologies related to neural networks such as PyTorch, TensorFlow, and flwr. I am excited to bring this project to its full potential, so if you are ready to join me on this journey, please do reach out!