Rapid Deployment of LLMs into Production - Strategies and Insights
Toronto Machine Learning Series (TMLS) via YouTube
Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Watch a conference talk from the Toronto Machine Learning Series where two PagerDuty experts share their journey of deploying Large Language Models (LLMs) into production within a tight two-month timeline. Discover practical strategies for identifying and validating LLM use cases, engineering effective prompts, and implementing comprehensive testing approaches. Learn about the development of a custom LLM Service that addresses critical aspects like security protocols, customer data protection, model flexibility, and system redundancy. Gain valuable insights into overcoming challenges such as limited planning time, evolving requirements, stakeholder management, and emerging technology adoption while coordinating multiple workflows. Understand how data science and machine learning engineering teams play crucial roles in successful LLM integration, focusing on security, testing, and monitoring considerations that drive AI-powered product innovation.
Syllabus
Rapid Deployment of LLMs into Production: Strategies and Insights
Taught by
Toronto Machine Learning Series (TMLS)