Architecture
Building GenAI Platform at DoorDash
Tuesday Jun 2 / 10:20AM EDT
When we started adopting LLMs across DoorDash, every team was implementing the same infrastructure: retry logic, fallback mechanisms, cost tracking, prompt versioning, and batch processing pipelines. Engineering time was wasted on repetitive plumbing work instead of building features.
Siddharth Kodwani
Tech Lead, AI Infrastructure @DoorDash
Swaroop Chitlur
Staff Engineer / Engineering Manager Machine Learning Platform @DoorDash
Beyond Prompting: Context Engineering for Production-Grade AI
Monday Jun 1 / 10:20AM EDT
If you're building production-grade AI apps, you may know an uncomfortable truth: reliable model outputs require far more than clever prompting.
Ricardo Ferreira
Principal Developer Advocate @Redis, Expert in Distributed Systems, Databases, and Software Development, Previously @AWS, @Elastic, and @Confluent
Adaptive Recommenders in the Real World: Inference, Evals, and System Design
Tuesday Jun 2 / 01:20PM EDT
Modern personalization systems are shifting from hand-tuned heuristics to AI-native architectures, but building an adaptive recommendation engine in production—one that continuously learns, evolves, and delivers measurable business value—requires far more than deploying a model.
Mallika Rao
Senior Engineering Manager @Zocdoc, Previously @Netflix, @Twitter and @Walmart