ESSENTIAL DUTIES: The successful candidate will work on big data analytics for surface and subsurface model and data integration. Much existing research on big data has focused on “big volume”, which has spawned research and implementation on highly scalable, fault-tolerant data processing. There is a recent realization that big data systems should also be able to absorb and process high-volume incoming data in real time or with low latency so that timely information and insights can be derived for critical applications with real-time constraints. The candidate will investigate the design and optimization of big and fast data analytics systems as applied to collecting, storing and processing field data relevant to monitoring trends and underlying interdependencies in surface and underground water ecosystems across large geographical areas. Work will involve (a) benchmarking large complex spatial-temporal and networked data analytics workloads, (b) innovating in popular large scale data processing and analytics platform, such as Hadoop, Spark, and TensorFlow, with new algorithms for analysis of complex water ecosystems, and (c) optimization under multiple objectives including latency, throughput, and cloud computing cost.