It Worked When I Prompted It - Challenges in LLM Production Deployment

Explore the challenges and solutions for deploying Large Language Models (LLMs) in production environments in this insightful 14-minute conference talk by Soham Chatterjee. Gain valuable insights into design patterns for successful LLM implementation, the importance of vector databases, and strategies for enhancing reliability and cost-effectiveness. Learn from Soham's expertise as he leads the machine learning team at Sleek, building tools for automated accounting and back-office management. Discover the intersection of machine learning and electronics, with a focus on TinyML and Edge Computing. Benefit from Soham's experience as an electrical engineer and course instructor, as he shares practical knowledge on navigating the complexities of moving LLM projects from proof-of-concept to production deployment.

It Worked When I Prompted It // Soham Chatterjee // LLMs in Production Conference Part 2