From Kernel to Codebase: Engineering Systems at Scale
Talk 1: Network Infrastructure at 10K+ Snapshotted VM Scale
Running thousands of snapshotted VMs pushes Linux networking to its limits. This talk covers battle-tested strategies balancing performance, isolation, and efficiency across large-scale topologies. Prashant & Shivendra will explore Geneve tunneling for scalable overlay networks, eBPF-accelerated networking for line-rate performance, and stateless NAT without connection tracking overhead. Prefix-based iptables/nftables rules scale to thousands of instances, while namespace pooling minimizes snapshot operation costs. They also address RTNL lock contention and its mitigation. Attendees will learn to architect network stacks for snapshotted workloads where VMs are cloned, restored, and migrated while maintaining security and predictable performance.
Talk 2: Evolution of Git
Git started as a distributed version control system designed to let developers work independently and exchange changes peer-to-peer. Two decades later, Git has evolved into the foundation of globally distributed development platforms, with centralized control planes, replicated storage, routing, sharding, and increasingly autonomous AI agents operating on repositories. Preetam explores that evolution—from Git’s original object model and replication primitives to modern architectures such as GitHub’s infrastructure, repository spokes, and AI-native development environments—and examines how the boundaries between version control and distributed systems are increasingly disappearing.
About Speakers
Prashant is an Ex-Principal Engineer specializing in distributed systems and serverless networking at AWS Lambda. Over 9 years of experience designing and delivering large-scale infrastructure solutions that power billions of invocations.
Shivendra is a Senior Engineering Leader at AWS Lambda where he owns the serverless compute primitives for Lambda, Athena, Glue, Bedrock and AuroraDSQL. Prior to AWS he worked at Microsoft, Wayfair, and Walgreens. He has a Masters in CS with specialization in Machine Learning from Georgia Tech. He has filed 6 patents in the serverless compute space.
With over 10 years of experience in software engineering, including 3+ years as a Staff Software Engineer at Uber, Preetam focuses on building scalable developer platforms and improving engineering productivity. At Uber, they have led major initiatives around cloud migration and developer workflows, including moving the Code Review Experience to GitHub. Previously, at Amazon, they worked across digital payments, merchant platforms, and microservices architecture.
Thank you Antithesis for making this event possible.