VESSL AI x Pinecone: LLMs in Production

​<LLMs in Production>

​​LLMs in Production is an AI product meetup hosted by VESSL AI and Pinecone. We bring together local founders, product leaders, and engineers to cover the best practices and the latest trends in Production LLMs.

​​Join our premiere event with SVB, where we will be joined by Koyeb, Snowflake, and more. We'll have food, drinks, and like-minded folks you can talk to about the roadblocks and solutions you've found along the way.

​​When & Where

• ​​When — Monday, September 9 at 6:00 PM
• ​​Where — SVB Experience Center, San Francisco

​​Agenda

• ​​(17:00~17:30) Doors open
• ​​(17:30~18:00) Building context-augmented LLMs with RAG & Vector DB
  • ​​Roie Schwaber-Cohen, Staff Developer Advocate, Pinecone
• ​​(18:00~18:30) Custom LLMs—smarter, faster, and cheaper
  • ​​Jaeman An, Co-founder & CEO, VESSL AI
• ​​(18:30~19:00) High-Performance LLMs: Serverless Deployment across Accelerators, GPUs, and CPUs
  • ​​Yann Leger, Co-founder & CEO, Koyeb
• ​​(19:00~ 19:30) Evaluating LLM Apps
  • ​​Anupam Datta, Principal Research Scientist for AI, Snowflake
• ​​(19:30~ 20:00) Multi-agent systems in production
  • ​​Laurie Voss, VP Developer Relations, LIamaIndex
• ​​(20:00~21:00) Networking with drinks & bite