Despite significant technological advancements, locating human survivors under debris in the aftermath of earthquakes remains a time-critical task for search and rescue teams, often delayed by the limitations of traditional search methods. These conventional methods’ inefficiency often results in longer rescue times, increasing the risk of fatalities. This paper proposes designing and implementing a novel handheld, Internet of Things (IoT) and Machine Learning-based portable earthquake survivor detector probe to enhance search and rescue operations. The proposed system utilizes a single-board edge computing device that integrates a range of sensors, including a thermal imaging camera, sound detection, and ultrasonic sensors. The data collected by these sensors is analyzed using machine learning algorithms to distinguish between living humans and nonliving objects. Additionally, a mobile application connected to a cloud database enables rescue teams and authorities to monitor the probe’s findings in real-time, facilitating faster decision-making and data access for coordination and evaluation.