Even though Moore’s law relevance in today’s world is a highly debated topic, we can’t deny the significant increase in computational power observed in affordable low-powered devices. Commodity hardware such as the Broadcom BCM2712 System-on-a-Chip which is powering the Raspberry Pi 5 is outperforming 15-year-old desktop class CPUs while only using a fraction of the power. This prompted a paradigm shift in the Internet of Things (IoT) world, moving away from relying entirely on cloud computing to performing as much of the computations on-device and on devices that are close by, thus marking the start of the edge-fog-cloud topology. Most edge computing platforms in the market have converged to using a containerization approach for scheduling workloads on edge devices which offers a great deal of flexibility by abstracting away the underlying platform but introduces CPU and memory overhead in an already resource-constrained environment. This paper aims to build on top of prior art introduced by the novel OpenEdgeCompute Framework [1] which is leveraging a simple orchestrator-worker pattern. We will perform a deep dive into the inner workings of the worker and its interactions with the orchestrator; additionally, we will analyze different design decisions that were made during the implementation phase such as the choice of a message passing interface or key abstractions needed to hide the implementation details from the outer world. To measure its effectiveness, we will benchmark the proposed solution using a simple echo application against a control edge computing framework that’s using containerization and capture key metrics such as cold boot times of the worker, end-to-end time for a cold-booted worker to process a request, CPU utilization and memory consumption.