Production AI at Scale: Cloudera's Journey in Building a Robust Inference Platform
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only! Grab it Explore a 37-minute conference talk that delves into Cloudera's AI Inference Service, a secure platform designed for generative AI and predictive inference workloads. Learn how Cloudera built their robust inference platform using Kubernetes, CNCF, and Apache open source projects, focusing on openness, security, scalability, performance, and standards compliance. Discover the architectural details of implementing production-grade AI inferencing in Big Data environments, including critical aspects such as performance optimization, scaling strategies, authentication mechanisms, fine-grained authorization, and audit logging procedures. Gain valuable insights from Cloudera's journey and experiences in developing a large-scale AI platform that successfully balances openness with security requirements.