Apoorva Joshi on LLM Application Evaluation and Performance Improvements

Jan 30, 2025

In this conversation, Apoorva Joshi, a Senior AI Developer Advocate at MongoDB with a rich background in cybersecurity and machine learning, delves into the intricacies of evaluating LLM applications. He discusses strategies for optimizing performance through observability and monitoring, and the evolution of LLMs from text generation to complex multimedia tasks. Joshi also highlights the importance of tailored evaluations for specific industries and makes a case for democratizing these models for broader accessibility.

Ask episode

AI Snips

Chapters

Transcript

Episode notes

ANECDOTE

Career Transition

Apoorva Joshi transitioned from a data scientist role to a developer advocate.
She enjoys writing, speaking, and interacting with customers about Generative AI.

INSIGHT

LLM Evolution

LLMs are shifting from text generation to other modalities like image, audio, and video generation.
Companies are adopting advanced techniques like hybrid search and parent document retrieval for LLM applications.

ADVICE

Building LLM Apps

Data, retrieval, LLMs, and monitoring are crucial for building LLM applications.
Consider advanced retrieval techniques and monitor applications for performance issues.

Get the Snipd Podcast app to discover more snips from this episode

Get the app