AI News
← Back to topics
3 research DoorDash single-source 1 article

DoorDash explores dynamic, moment-aware personalization with LLMs

DoorDash describes a hybrid approach using LLMs for consumer profiles and blueprints with deep learning for ranking to capture short-lived user intent.

DoorDash explores dynamic, moment-aware personalization with LLMs
via InfoQ AI/ML/Data Engineering

🔍 Let's dive in

Sudeep Das and Pradeep Muthukrishnan outline a hybrid system at DoorDash that leverages LLMs to generate natural-language consumer profiles and content blueprints. Traditional deep learning components handle last-mile ranking to optimize recommendations. The approach aims to adapt to transient user intent and large catalog abundance through joint use of LLMs and DL models.

Lead coverage: InfoQ AI/ML/Data Engineering — Presentation: Dynamic Moments: Weaving LLMs into Deep Personalization at DoorDash ↗

🕰 The timeline · 1 source

InfoQ AI/ML/Data Engineering reporting rumored · 2d ago · 3/5

Presentation: Dynamic Moments: Weaving LLMs into Deep Personalization at DoorDash ↗

Sudeep Das and Pradeep Muthukrishnan outline a hybrid system at DoorDash that leverages LLMs to generate natural-language consumer profiles and content blueprints. Traditional deep learning components handle last-mile ranking to optimize recommendations. The approach aims to adapt to transient user intent and large catalog abundance through joint use of LLMs and DL models.

🏷 Tags

software-developmentconsumerenterprise

🔧 Debug

Cluster ID
2fb5866ade
Importance (max)
3
Members
1
Sources
InfoQ AI/ML/Data Engineering
Earliest
2026-04-21T10:35:00.000Z
Latest
2026-04-21T10:35:00.000Z
Lead URL
https://www.infoq.com/presentations/llm-personalization