In this episode of Talking Serverless, we sit down with Jack Pertschuk, Principal Engineer of Algorithms and Platforms at Pinecone, to explore the ever-evolving landscape of LLM-centric architectures and vector databases.

Jack shares his journey from data science to building cutting-edge infrastructure at Pinecone, and walks us through what it really means to architect apps in a world where large language models are at the center.

💡 In this episode:

-What it takes to build reliable, scalable LLM applications

-How to think about infrastructure when your “data” lives in high-dimensional space

-What makes Pinecone tick behind the scenes

Connect with Jack:

Linkedin: https://www.linkedin.com/in/jack-pertschuk-833196114/

X: https://x.com/jack_pertschuk

About Pinecone:

Pinecone is the leading vector database for building accurate and performant AI applications at scale in production.

Pinecone was created to provide the critical storage and retrieval infrastructure needed for building and running state-of-the-art AI applications. The founding principle was to make the solution accessible to engineering teams of all sizes and levels of AI expertise, which led to the fully managed service and ease of use that Pinecone is known for today.