Edge AI Inference Architect - Low-Latency Model Serving

Tether Operations in Bogotá, Colombia, is seeking a qualified member for their AI model team to drive innovation in model serving architectures for advanced AI systems. The role involves optimizing model deployment strategies to deliver efficient performance across real-world applications, focusing on both high-resource and resource-constrained environments.

The ideal candidate holds a degree in Computer Science and preferably a PhD in a related field such as NLP or Machine Learning. The position demands expertise in designing model serving pipelines and inference algorithms, as well as a robust background in empirical research.