Multi stage deep network for image classification

Hi, I would like to hire someone to implement a deep learning architecture for image classification. It’s not as simple as having an input, a cnn model and output predictions. You really need to be excellent in coding and very knowledgeable in deep learning and the technical details. Blocks included:
Attention modules (nn.multiheadattention) and variational autoencoder.

I’d appreciate someone who can start asap. Thanks!