Choosing the Right LLM and Optimizing GenAI Performance

It’s been over a year since GenAI hit the market, and Gartner has estimated that only 10% of generative AI solutions have made it to production. Such roadblocks range from difficulty testing to poor observability, to knowing which LLM is the best to use to the development and management process presenting new challenges for time-crunched data science teams. Join VP of Field CTOs Lisa Aguilar, and Jess Lin Lead GenAI Data Scientist, as they explore the two biggest decisions facing aspiring AI teams: how to choose the right LLM and how to compare and optimize GenAI performance. She’ll share: -How to evaluate commercial versus open-source models -How to balance cost, performance, and risk management factors -How to benchmark your GenAI experiments against performance and quality metrics -How to build effective (and sustainable) intervention and moderation strategies Attendees will also see the real-world impact of AI with a behind-the-scenes look at digital consultancy for sustainable growth BSI and how they reduced model development time by 67%.