Chris Fregly is a US AI engineer (formerly at AWS, Databricks, and Netflix) and one of the more prolific independent voices on the production-engineering side of large-scale AI systems. He is the co-author of Generative AI on AWS (O'Reilly) and runs the popular Data Science on AWS meetup network.
His CourseFlix listing carries AI Systems Performance Engineering — a focused treatment of the performance-engineering discipline applied to AI systems: latency optimisation, throughput tuning, GPU utilisation, distributed inference, and the operational patterns for running AI workloads at scale.
Material is paid and aimed at engineers running AI systems in production. For broader content, see CourseFlix's AI App Building category page.