Presentation: Building GenAI Platform at DoorDash
Swaroop Chitlur and Sidd Kodwani share DoorDash’s journey building an internal GenAI platform. They discuss core architectural bets, transitioning from vendor-first setups to open-weights models, navigating LLM and agent gateways, and balancing accuracy, latency, and cost for over 5,000 internal users. By Siddharth Kodwani, Swaroop Chitlur
InfoQ Presents: Building GenAI Platform at DoorDash
Swaroop Chitlur and Sidd Kodwani detail DoorDash's journey in creating an internal GenAI platform, focusing on architectural decisions, transitioning to open-weights models, handling LLM and agent gateways, and balancing accuracy, latency, and cost for 5,000+ internal users. Sidd Kodwani, a Software Engineer on the GenAI Platform team, discusses infrastructure for AI agents, while Swaroop Chitlur leads the Generative AI Platform, overseeing LLM inference, fine-tuning, evaluations, and AI agents.
The presentation, part of QCon AI, emphasizes principles like being customer-obsessed, focusing on end-to-end workflows, and providing business value through accuracy, latency, and cost optimization.
Written by urgent.news from InfoQ's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
