Productionizing Custom LLMs

November 16th, 2023, 5:00-7:30 p.m. PT| San Francisco, CA
In case you haven’t heard, the future of AI is likely to be smaller, use-case specific LLMs that are great at specific tasks and cost far less to run than prototypes built in large LLMs like ChatGPT. But how do you get them to production?

Join us (in person!) for an expert panel of product and data science practitioners who are currently building custom AI/ML and generative AI to hear about the challenges, work-arounds, solutions and best practices involved in getting to production.
#Happy Hour

Great for: Data scientists, AI Product Managers & AI/ML Product teams

Charlene Chambliss
Nina Lopatina
Software Engineer, Aquarium
Director of Data Science, Nurdle
Deepak Ramachandran
Staff Research Engineer, Google
Key topics we’ll cover include
Business use-cases and evaluating quality
Identifying performance issues from context to content
What is and when to use fine-tuning vs RAG – or both – to fix it
Evaluation - Testing data and process
Getting models and generative LLMs to perform well in multiple languages
How to get compliant datasets for training so you don’t get sued
Additionally we’ll be in a swanky bar with good drinks so networking with your fellow AI builders will feel civilized and look good on social media!

This is a great event for both AI product managers as well as data scientists as we’ll cover both the high-level requirements and milestones as well as some details around model optimization and data quality/sourcing (PMs can go to the bar during this part!).
The happy hour has limited space. Fill out the form to reserve your spot.