Technical Talks

Raghotham Murthy
Raghotham Murthy
Software Engineer, Llama | Meta
Ashwin Bharambe
Ashwin Bharambe
Software Engineer, Llamastack | Meta
Hardik Shah
Hardik Shah
AI Engineer | Meta

Building LLM Applications with Llama Stack

video
Missing value detected...
Video will be populated after the conference

  • Foundation Models

In this talk, we will describe what it takes to build production grade LLM applications. Unlike regular applications, LLM applications are non-deterministic, and require a unique set of building blocks to support the full software development lifecycle from building to testing to deploying to monitoring to then improving the application. We will show how Llama Stack can be used to build and improve LLM applications in different environments – local development, cloud, on-prem, and mobile.

Raghotham Murthy

Software Engineer, Llama

Raghotham Murthy

Meta

Raghotham Murthy is an engineer at Meta focusing on Llama OSS and Llama Stack development. He serves as an Apache Hive PMC Member since 2008 and advisor to NextData Technologies, where he previously was Founding CTO. His entrepreneurial background includes founding datacoral Inc, a serverless data integrations platform that was acquired by Cloudera. At Cloudera, he served as Corporate Vice President of Innovation Accelerator. Raghotham holds a Master of Science in Computer Science from Stanford University and began doctoral studies before leaving to pursue entrepreneurial ventures in the data engineering space.

Ashwin Bharambe

Software Engineer, Llamastack

Ashwin Bharambe

Meta

Ashwin Barambe is Technical Lead for Llama Stack at Meta, driving the development and implementation of Meta's open-source AI infrastructure that powers large language model applications at scale. A contributor to Meta's Llama 3 and Llama 4 model families, with expertise in distributed systems and machine learning infrastructure. Ashwin leads the technical vision for Llama Stack, making advanced AI capabilities more accessible and efficient for developers worldwide. His work focuses on optimizing performance, scalability, and usability of the Llama ecosystem, enabling organizations to leverage state-of-the-art language models in production environments.

Hardik Shah

AI Engineer

Hardik Shah

Meta

Hardik Shah is a Software Engineer at Meta with a tenure of 8+ years and has worked on various AI projects from computer vision (alt text for visually impaired) to AI on Ray Ban Meta glasses and now on Llama. Currently a core developer on Llama Stack.