We are excited to announce the third night of talks in the NYC Systems series! Talks are agnostic of language, framework, operating system, etc. And they are focused on engineering challenges, not product pitches.
We are pleased to have Haikal Vahab Jabrayilov and Oz Katz speak, and glad to have Trail of Bits as a partner for the venue.
Vahab Jabrayilov is a Computer Science PhD student at Columbia University, advised by Professor Kostis Kaffes. He specializes in performance optimization for computer systems, focusing on designing scheduling solutions across end-host, rack, and cluster scales to minimize microsecond-scale tail latency. More recently, his work has expanded to include accelerating machine learning systems.
Modern cloud applications need microsecond-level responsiveness, yet current virtualization approaches often cause millisecond-scale delays. This talk presents two complementary solutions that bring virtualized environments closer to bare-metal performance.
First, Machnet is a userspace network stack designed for public clouds. Rather than relying on specialized NIC features unavailable in virtual NICs, Machnet uses a “Least Common Denominator” approach and a microkernel design to support flexible execution models. It achieves substantial latency and CPU efficiency gains, demonstrating 80% lower latency and 75% lower CPU utilization for a key-value store compared to today’s best solutions.
Second, Rorke is a microsecond-scale VM scheduler for oversubscribed cloud environments. By approximating processor sharing at the host and dynamically adapting time slices, Rorke cuts tail latency by over 10× for popular low-latency workloads—without harming throughput in non-oversubscribed scenarios. Together, Rorke and Machnet bring virtualized infrastructure closer than ever to bare-metal levels of performance, setting a new standard for cloud computing efficiency.
Oz Katz is the CTO and co-founder of lakeFS, the open source platform bringing Git-like version control to petabyte-scale data lakes. Previously, Oz led Data and Infrastructure as VP R&D at SimilarWeb (NYSE: SMWB), scaling systems to handle internet-wide analytics. Oz joined SimilarWeb through its acquisition of Swayy, a content analytics startup he co-founded.
With deep expertise in distributed systems and data infrastructure, Oz is passionate about making data and AI engineering as agile and collaborative as software development.
In Git, branching is instant and merging scales with your changes - not the size of your repository. Now imagine those same guarantees applied to petabytes of data and billions of objects.
This talk shows how lakeFS brings Git-like semantics to massive data lakes, delivering constant-time branching and atomic commits directly on cloud object storage. We'll dive into the metadata structures, commit algorithms, and concurrency controls that make it possible - as well as examine the trade-offs and engineering decisions behind achieving "Git-speed" at planetary scale.