Stephan Dollberg is a Performance Engineer with 13 years of experience building and optimizing low-latency, high-throughput systems across financial trading, edge networking, and streaming platforms. He specializes in C++-level performance work—refactoring core loops, memory allocators, and serialization—and has contributed to high-profile open-source projects like Redpanda and Seastar where his changes reduced bottlenecks and improved observability. At G-Research he tuned ultra-low-latency trading systems, and at Cloudflare he helped implement an HTTP rate-limiting product that mitigated massive request floods. Based in the UK with degrees from TUM and ETH Zurich, he combines systems-level rigor with pragmatic tooling (including memory samplers and micro-benchmarks) to make “bits move” measurably faster.
13 years of coding experience
8 years of employment as a software developer
Bachelor of Science - BS, Electrical Engineering and Information Technology, 1.7, Bachelor of Science - BS, Electrical Engineering and Information Technology, 1.7 at Technical University Munich
Master of Science - MS, Electrical Engineering and Information Technology, 5.4, Master of Science - MS, Electrical Engineering and Information Technology, 5.4 at ETH Zurich
Redpanda is a streaming data platform for developers. Kafka API compatible. 10x faster. No ZooKeeper. No JVM!
Role in this project:
Back-end Developer & Performance Engineer
Contributions:754 reviews, 220 PRs, 301 pushes in 1 year 11 months
Contributions summary:Stephan primarily focused on performance improvements and optimization within the Redpanda streaming data platform. Their commits demonstrate expertise in C++ by refactoring code, switching to more performant data structures like `chunked_hash_map`, and optimizing core components such as the raft and kvstore. They addressed performance bottlenecks by improving serialization and addressing potential reactor stalls. Additionally, the user enhanced the observability of the system by adding metrics and monitoring tools for memory usage and batch sizes.
High performance server-side application framework
Role in this project:
Back-end Developer / Performance Engineer
Contributions:36 reviews, 14 PRs, 73 comments in 1 year 7 months
Contributions summary:Stephan primarily focused on optimizing the performance and stability of the `seastar` framework. Their contributions involved fixing performance bottlenecks within the core loop and TLS implementations, addressing potential busy-spinning issues in the epoll backend, and enhancing the memory allocation system. The user also added micro-benchmarks to test the allocator, demonstrating a focus on low-level system performance. Several changes involved adapting the memory sampler to efficiently track and profile memory allocations.
seastarc-plus-plusdpdkframeworkperformance
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.
Request Free Trial
Stephan Dollberg - Performance Engineer at Redpanda Data