Gateway nodes are important elements in a sensor network since they provide the ability to establish long range reach-back communication in order to retrieve critical data to remote locations. In a sensor network composed of thousands of sensors, the gateways allow information to be transmitted to an UAV flying in high altitude or to a head-quarter command center that is 20~km away from the sensor network. The gateways are however, prone to failures just like regular sensor nodes, and they consume significantly more energy since they transmit over longer distances compared with sensor-to-sensor links. We introduce an adaptive and fault-tolerant method for gateway assignment in sensor networks. Our approach is fully distributed and achieves the following objectives: (i) It allows surviving gateways to recover for other gateways that have failed. (ii) It distributes energy usage and traffic load between several gateway nodes within the sensor network. Each gateway adaptively controls its region of influence based on local conditions such as energy level and traffic load. Our methodology was evaluated via simulation using a network model containing 400 sensor nodes with virtual targets. The simulation results indicate that our scheme is robust to gateway failures. Moreover, when there are no gateway failures, our scheme successfully balances the energy consumption and traffic load among the gateways.