David Marchevsky is a software engineer with 12 years of experience building backend systems at notable tech companies including Facebook, BuzzFeed, and bitly. Based in New York, he brings deep systems and low-level tooling expertise, evidenced by substantive open-source contributions to prominent BPF projects like iovisor/bcc and libbpf where he enhanced USDT support, x64 register handling, and tracing helpers. He combines practical production experience with careful refactoring and API improvements that prioritize maintainability and observability. Collected from roles spanning startups to large platforms, his work reflects a strong emphasis on performance-sensitive instrumentation and developer-facing tooling.
12 years of coding experience
8 years of employment as a software developer
Bachelor of Science (BS), Computer Science, Bachelor of Science (BS), Computer Science at The George Washington University
BCC - Tools for BPF-based Linux IO analysis, networking, monitoring, and more
Role in this project:
Back-end Developer
Contributions:91 reviews, 161 commits, 170 PRs in 3 years 9 months
Contributions summary:David primarily focused on enhancing the `bcc` toolset, specifically within the context of USDT (User Statically Defined Tracing). Their contributions include modifications to support xmm registers for x64 architecture and enhancements to the underlying symbol resolution mechanisms. These changes involved code adjustments in multiple source files, including `usdt.cc`, `bcc_syms.cc`, and API-related files, demonstrating a deep understanding of the project's core functionalities. They also refactored code to improve maintainability, such as pulling out enums and refactoring file operations for the ClangLoader.
Automated upstream mirror for libbpf stand-alone build.
Role in this project:
Backend Developer
Contributions:10 commits, 1 PR, 3 comments in 11 months
Contributions summary:David's commits primarily focus on modifying and improving the libbpf library, particularly concerning BPF (Berkeley Packet Filter) functionality. They introduced the `bpf_trace_vprintk` helper and refactored the `bpf_printk` macro, demonstrating expertise in BPF tracing. The user also addressed code clarity and efficiency by clarifying parameter requirements, migrating to `static const` strings, and deprecating older APIs. Furthermore, the user added a field to `bpf_prog_info` to expose a verified instructions count.
bpfstand-alonestandtracingebpf
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.