Remote AI Research Engineer - Model Compression & Inference

Tether in Rome is seeking a skilled AI model team member to drive innovation in model serving and inference architectures for advanced AI systems. You will design, deploy, and optimize model serving pipelines ensuring high throughput and low latency across diverse environments.

The ideal candidate will have a PhD in NLP or Machine Learning and proven experience with inference optimization on mobile devices. Join Tether and be part of pioneering a global financial revolution.