Open ANR Postdoctoral Position at ENTPE-LICIT (Lyon-France)

Guaranteeing efficient, resilient and sustainable mobility in modern large cities is a very challenging task, due to growing transport demand, climate changes, industrialization and population increase.
Distributed and real-time monitoring of large-scale multi-modal transport systems is emerging as a solution to meet such demands, thus providing transport actors with novel decision-making tools for more effectively managing mobility, by reducing costs and guaranteeing higher-quality services.
The LICIT laboratory of University of Lyon, ENTPE and IFSTTAR is working with academic (INSA-Lyon, INRIA, LIRIS, CNR-Italy, University of Illinois Chicago, University of Sannio, University of Tartu) and industrial partners (Orange, Lyon Metropole) in the framework of the French ANR project “PROMENADE” (Platform for Resilient Multi-modal Mobility via Multi-layer Networks & Real-time Big-Data Processing).
The PROMENADE project aims to improve transport resilience via big real-time data monitoring, complex networks and machine learning solutions by disposing of large-scale and multi-source datasets on human mobility.
An open source customisable and extensible platform will be proposed to address the different challenges related to engineering the resilience of large-scale urban transport networks, by integrating tools, algorithms and components to perform heterogeneous data collection (IoT sensors, server APIs, mobile networks, social networks, etc.), big data processing and multi-source data mining.
In this context, we are looking for an enthusiastic postdoc with strong background in Distributed Systems Design, IoT and Big Data Processing as well as in Software Engineering, and with an interest and skills in Machine Learning and Data Analysis.
*** DESCRIPTION OF THE POSTDOC ACTIVITIES ***
• The goal of this postdoc is to contribute to the design and prototyping of the architecture of the PROMENADE platform, as well as to the development of the algorithms and solutions for data-driven mobility and network analysis.
• The postdoc will also be involved in supporting the activities of three PhD students, whose thesis topics are related respectively to:
• developing a data-driven modelling framework for (real-time) reconstruction and analysis of mobility practices from multi-source data;
• complex network engineering of large-scale approaches for real-time computation of resilience metrics;
• definition of new resilience indicators for multi-modal transport networks via simulation-driven stress testing and dynamic control strategies for new generation resilient transport networks and systems.
• The postdoc could be involved in teaching activities related to Intelligent Transportation Systems, Data mining and machine learning.
The platform will be implemented by using multiple technologies suited for big data processing, machine learning and IoT integration (Spark, Scala, Python, Kubernetes, etc.).
*** REQUIREMENTS ***
• The candidate shall hold a PhD in Computer Science, on a topic related to big data, distributed computing, scalable software engineering, machine learning for big data.
• Proven experience on IoT, Big Data Architectures and Technologies (Big Data processing and management) and distributed systems: Hadoop, Spark, Scala, Kubernetes, HBase;
• Good scripting and coding skills (bash, java, scala, pyspark, python);
• Autonomous and team working capabilities.
*** OFFER DETAILS ***
• The postdoc will have the opportunity to work in a stimulating research environment including both academic and industrial collaborations, to participate to both computer science and transportation conferences, as well as spending short abroad research periods in the partner institutions.
• Duration: 12 months (with possibility of an extension to 18 months)
• Net Salary: 2,000 – 2,300 € per month depending on the experience.
• Start Date: end of 2019/beginning of 2020.
• Hosting team: LICIT laboratory (http://licit.ifsttar.fr), Lyon, France (EU).
*** APPLICATION INSTRUCTIONS ***
Applications in PDF format or informal enquiries by email to angelo.furno-AT-ifsttar.fr are welcome.
Applications, written in English should include:
• Curriculum Vitae (including your contact address, work experience, publications, software repositories)
• Cover letter
Deadline for applications: 30 October 2019.
Screening of applications starts immediately and will continue until the position is filled. Therefore, early applications are encouraged.
The starting date is negotiable, but preferably it is fixed on November 1st, 2019.
*** REFERENCES ***
Some recent papers of the team in line with the scope of the PROMENADE project and the required post-doc profile:
• Katsikouli P., Fiore M., Furno A., Stanica R. (2019, June). Characterizing and Removing Oscillations in Mobile Phone Location Data. In 2019 IEEE 20th International Symposium on "A World of Wireless, Mobile and Multimedia Networks" (WoWMoM).
• Castiello A., Fucci G., Furno A., Zimeo E. (2018, December). Scalability Analysis of Cluster-based Betweenness Computation in Large Weighted Graphs. In 2018 IEEE International Conference on Big Data (Big Data).
• Furno A., El Faouzi N.E., Sharma R., Zimeo E. (2018, December). Fast Approximated Betweenness Centrality of Directed and Weighted Graphs. In 2018 International Conference on Complex Networks and their Applications. Springer International Publishing.
• Henry E., Bonnetain L., Furno A., El Faouzi N.E., Zimeo E. (2019, June). Spatio-temporal Correlations of Betweenness Centrality and Traffic Metrics. In 6th International Conference on Models and Technologies for Intelligent Transportation Systems (MT-ITS).
• Fekih M., Bellemans T., Smoreda Z., Bonnel P., Furno A., Galland S. (2019, January). Suitability of Cellular Network Signaling Data for Origin-Destination Matrix Construction: A Case Study of Lyon Region (France). In 98th Transportation Research Board Annual Meeting (TRB).
• Bonnetain L., Furno A., Krug J., El Faouzi N.E. (2019, January). Can we map-match individual cellular network signaling trajectories in urban environments? A data-driven study. In Transportation Research Record (TRR).
• Gauthier P., Furno A., El Faouzi N.E. (2018, August). Road network resilience: how to identify critical links in presence of day-to-day disruptions?. In Transportation Research Record (TRR).