Dumanshu Goyal

Speaker: Dumanshu Goyal

He / him / his

Uber Technical Lead @Airbnb Powering $11B Transactions, Formerly @Google and @AWS

Dumanshu Goyal is a Senior Principal Engineer at AWS, building databases for the agentic AI era and shaping architecture across AWS database services. Previously, he led Online Data at Airbnb, powering its $11B transaction platform and building the next generation of the company’s data systems. Before that, he led in-memory caching for Google Cloud Databases, delivering 10x improvements in scale and price-performance for Google Cloud Memorystore, one of the rare times “10x” was more than a slide promise.

Earlier, he spent 10 years at AWS as the founding engineer of AWS Timestream, a serverless time-series database, and architected durability and availability features for AWS DynamoDB, one of the internet’s foundational data services.

Over nearly two decades, Dumanshu has built and operationalized large-scale distributed systems spanning millions of QPS, businesses scaling from nine figures into the billions, organizations from tens to hundreds of engineers, and 20+ patents in distributed systems. His focus is technical leverage: architectural changes that improve not just one workload, but an entire class of systems.

Find Dumanshu Goyal at:

Session

From ms to µs: OSS Valkey Architecture Patterns for Modern AI

As AI applications demand faster and more intelligent data access, traditional caching strategies are hitting performance and reliability limits.

Read more

Date

Wednesday Nov 19 / 02:45PM PST ( 50 minutes )

Location

Ballroom A

Topics

Architecture Open Source Microsecond-Scale In-memory Caching Sharded System Reliability Staff Plus Engineering Platform Engineering

Share