Connected vehicles and new paradigms in the mobility sector have recently pushed forward the need for accuratelyidentifying who is behind the steering wheel on any drivingsituation. Driver Identification becomes part of a building blockin the mobility area to enable new smart services for mobility likedynamic pricing for insurance, customization of driving featuresand pay-as-you-drive services. However, existing methods fordriver identification depends on complex and high sample-ratevehicle data coming either from CAN-bus or from externaldevices. In this paper we propose to explore the potential forhigh accuracy driver identification with low-cost and low-sampleddata, mainly GPS trajectories. Using a deep-learning basedapproach, we obtain overall error-rate of 1.9, 3.87, 5.71, 9.57, 13.5% for groups of 5, 10, 20, 50, 100 drivers. The results show outstanding accuracy and performance, enabling a fast and low-complex deployment.