Cover Image for Operationalizing LLMs: From Prototype to Production

Presented by

Data Phoenix is a live media platform for AI and Data professionals, covering technologies under the hood, best practices, and live demos from the builders shaping the industry, via original shows.

Hosted By

Operationalizing LLMs: From Prototype to Production

Data Phoenix

Virtual

Past Event

Welcome! To join the event, please register below.

About Event

At Instacart, large language models (LLMs) play a crucial role in enhancing the grocery shopping experience and streamlining support for both customers and shoppers. Two key use cases showcase the transformative potential of AI:

AI-Generated Recipes: Instacart employs LLMs to create recipes based on top SEO-searched keywords, ensuring relevance in online searches and customer engagement. These AI-generated recipes are paired with visually appealing, AI-created images to further captivate users and enhance discoverability. This involves developing a complex AI recipe ingestion pipeline.
AI-Powered Chatbot: Instacart leverages LLMs at scale to build intelligent chatbots that address customer and shopper inquiries efficiently. By understanding context and providing accurate, conversational responses, these chatbots solve issues ranging from order updates to product guidance, reducing support friction.

Both use cases highlight how LLMs are driving innovation and operational efficiency in a fast-paced, customer-centric environment.

Speakers

Yogiraj Awati — Engineering Manager at Instacart. Yogiraj is a seasoned technology leader with over a decade of expertise in distributed computing, Agentic AI, and large language models (LLMs). As part of Instacart’s leadership team, he is driving the transformation of grocery shopping through cutting-edge AI solutions, digitizing customer experiences, and empowering retailers with a comprehensive suite of AI-powered offerings.

Previously, Yogiraj contributed to Amazon Web Services (AWS) as a founding member of the AWS X-Ray team, where he helped develop it into a leading observability service.

Launch partner

AgentField is open-source infrastructure for building autonomous software factories and the AI backends that power them. It gives multi-agent systems a single control plane for orchestration, governance, and provenance - so every action your agents take is policy-checked and accountable, with no glue code and no editable logs. Apache 2.0, with SDKs in Python, TypeScript, and Go.

Partners

KROK
The AI Collective is a global non-profit building the human layer for the AI era. We unite 200,000+ leaders, builders, and stakeholders across 150+ forums worldwide to democratize the frontier, build trust, and coordinate how society navigates the rapid acceleration of technological progress.