Piotr Prokop
Senior System Software Engineer at NVIDIA
Gdańsk, Pomeranian Voivodeship, Poland
Summary
🤩
Rockstar🎓
Top SchoolPiotr Prokop is a Senior System Software Engineer with 11 years of experience building cloud-native infrastructure and low-level system integrations, currently at NVIDIA in Gdańsk. He is fluent in Go, Python and Bash and has deep hands-on expertise across container orchestration, storage and virtualization technologies including Kubernetes, Docker, Ceph, OpenStack and Terraform. Piotr has contributed upstream to Kubernetes projects—implementing NUMA-aware scheduling policies and enhancing the topology manager and scheduler-plugins—demonstrating a focus on performance-sensitive resource management. He has led architecture and implementation work for production services at companies like Nike and Intel, including building Kubernetes operators and bare-metal NVMeoF solutions. Known for bridging system internals with operator-friendly tooling, he often translates low-level resource topology concepts into configurable platform features. His background in telecommunications and informatics gives him a pragmatic systems-thinking approach to complex distributed infrastructure problems.
11 years of coding experience
7 years of employment as a software developer
Bachelor of Engineering (BE), Telecommunications Engineering, Bachelor of Engineering (BE), Telecommunications Engineering at Gdańsk University of Technology
English, German, Polish
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (14)
kubernetes10
container10
go10
resource-management10
kubernetes-pods10
system-design9
data-structure9
software-design9
sys9
algorithm9
data-structures9
algorithms9
api8
apidoc8
Programming languages (9)
Github contributions (5)
kubernetes-sigs/scheduler-plugins
Dec 2022 - Jan 2023
Repository for out-of-tree scheduler plugins based on scheduler framework.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:154 reviews, 7 commits, 11 PRs in 1 month
Contributions summary:Piotr primarily contributed to the node resource topology plugin by implementing new scoring strategies and filter handlers. They integrated the `LeastNUMANodes` scoring strategy and split the topology matching handlers into scoring and filter functions, allowing for separate configuration based on Kubernetes node policies. Furthermore, the user updated dependencies within the project, including upgrading the `noderesourcetopology-api` package and the `gonum` package. This indicates a focus on plugin functionality and dependency management within the Kubernetes scheduling framework.
schedulerk8s-sig-schedulingout-of-tree
kubernetes/kubernetes
Oct 2022 - Nov 2022
Production-Grade Container Scheduling and Management
Role in this project:Back-end Developer
Back-end DeveloperContributions:56 reviews, 6 commits, 12 PRs in 1 month
Contributions summary:Piotr contributed to the Kubernetes project by introducing new configuration options for the Topology Manager, specifically adding a new flag and options for fine-tuning its behavior. Their work involved modifying Kubelet configuration files, generated OpenAPI definitions, and associated code, demonstrating a focus on system-level configuration and resource management within the Kubernetes ecosystem. Furthermore, the user added NUMA information and implemented the closest NUMA policy, indicating involvement in optimizing resource allocation and improving multi-NUMA alignment. These contributions suggest a focus on enhancing the performance and efficiency of Kubernetes resource scheduling.
containersschedulingdockergradeproduction-grade
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.