Artificial Intelligence

Pierre Lienhart

Author: Pierre Lienhart

Pierre Lienhart is a Senior Machine Learning Engineer at the AWS Generative AI Innovation Center in London. With three years of experience at Amazon, he has guided customers across every major industry in running their inference workloads on the most cost-effective AWS infrastructure for their needs. He brings deep expertise in scaling high-performance inference across AWS Trainium and GPU platforms.

How Deepgram optimized voice AI at scale with AWS Trainium

How Deepgram optimized voice AI at scale with AWS Trainium

Deepgram worked with the AWS Forward Deployed Engineering team to port its Nova-3 speech-to-text model to AWS Trainium2 for offline batch inference. This post covers porting to the AWS Neuron stack, kernel-level tuning, a data-parallel Rust runtime, and the throughput and cost results on batch transcription.