Marcelo Ayaviri is an IT Specialist with over a decade at IBM, currently consulting in Lab Services for Storage from São Paulo and blending deep product knowledge with hands-on customer engineering. He began in IBM Customer Support where he honed problem determination, crisis management, cross‑cultural teamwork, and clear technical communication, then transitioned to face‑to‑face consulting, training, and pre‑sales strategy across Latin America and the US. Marcelo has broad expertise across the IBM Storage portfolio—software‑defined storage, SANs, copy services, tape systems, and InfiniBand—and is comfortable across Windows, AIX, Linux and Oracle/DB2 environments. Beyond enterprise storage he contributes to cloud-native open source projects like KubeVirt and Kepler, adding performance tests, monitoring enhancements, and eBPF-driven power measurements that reflect a performance- and observability-first mindset. He combines field-proven customer advisory skills with low-level systems insight, making him effective at translating operational needs into technical strategy and measurable outcomes.
10 years of coding experience
Sistemas de Informacao, Data Processing, Sistemas de Informacao, Data Processing at Centro Universitário FIEO
Kepler (Kubernetes-based Efficient Power Level Exporter) uses eBPF to probe performance counters and other system stats, use ML models to estimate workload energy consumption based on these stats, and exports them as Prometheus metrics
Role in this project:
Back-end & DevOps Engineer
Contributions:461 reviews, 115 commits, 161 PRs in 9 months
Contributions summary:Marcelo primarily contributed to the Kepler project by removing duplicate code, updating metrics, and refactoring components related to power consumption measurement. Their work involved updating the RAPL sysfs event detection, fixing Prometheus metric types, and modifying the BPF code to collect CPU time per CPU. Additionally, they refactored the power package and updated dependencies to improve efficiency and maintainability within the system.
Kubernetes Virtualization API and runtime in order to define and manage virtual machines.
Role in this project:
Backend & DevOps Engineer
Contributions:138 reviews, 59 commits, 20 PRs in 1 year 8 months
Contributions summary:Marcelo contributed to the KubeVirt project by implementing new metrics for workqueue and updating the virt-handler configuration, improving monitoring capabilities. They added a performance density test and related scripts, indicating involvement in performance testing and automation. The user also added support for configuring the virtual-launcher qemu-timeout, and added migration tracking for phase transitions.
apivmsmachineslibvirtruntime
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.