Navigation and service

Advertising division: JSC - Jülich Supercomputing Centre
Reference number: 2018-200

test

The Jülich Supercomputing Centre (JSC) at Forschungszentrum Jülich operates one of the most powerful supercomputer infrastructures for scientific and technical applications in Europe and grants scientists in Germany and Europe access to these resources for their research. The department of Federated Systems and Data at JSC develops software for data analysis, data management and workflow management on distributed data and compute systems. The research group Earth System Data Exploration applies these tools to develop new analysis methods for Earth System data with a focus on Deep Machine Learning. Together with the “Helmholtz Analytics Framework” the group is promoting these methods to web-based services for the global scientific community. The ERC Advanced Grant “IntelliAQ” specifically aims at applying state-of-the-art machine learning techniques to the comprehensive database from the “Tropospheric Ozone Assessment Report” to obtain improved and robust information on global air quality and its changes with time. The „IntelliAQ“ project compiles a globally unique database with long-term measurements of air pollutant concentrations around the world. These observational data are labeled with a comprehensive set of metadata and can be combined with data from numerical weather models and satellite retrievals to allow for characterization of measurement sites and air pollution episodes. Together, these data comprise several Terabytes, which can be fed into deep neural networks for training and validation. Machine learning shall be used to interpolate air quality data in space and time and generate short-term forecasts.

We are looking to recruit a

Postdoctoral fellow to develop Deep Learning Methods for the analysis of global air quality data

Your Job:

  • Selection of suitable neural network architectures and implementation on Jülich computer systems
  • Independent monitoring of the research questions that arise, e.g. the use of unsupervised learning, the optimisation of hyperparameters or the determination of probability densities
  • Publication of your results at relevant conferences and in trade journals
  • Supporting the PhD students employed in the project in methodological and technical questions concerning machine learning
  • Working closely with other team members to transform your results into quasi-operational data services

Your Profile:

  • Doctorate degree from a university with internationally accepted quality standards in informatics, mathematics, or a related subject
  • Profound experience with modern machine learning methods (deep hierarchical networks, CNN, LSTM, GAN), as documented in your dissertation and publications
  • Scientific curiosity with respect to environmental research questions related to air quality or climate change
  • Profound knowledge of statistical methods such as timeseries analysis, regression, auto-correlation, multivariate statistics, and error analysis
  • Experience in software development and programming languages such as Python, C++, or R
  • Knowledge of the UNIX/Linux operating system
  • Ability and willingness to intensely collaborate with the members of the research group and international colleagues
  • Willingness to pass your knowledge of machine learning to team members and contribute to their education in this area
  • Very good knowledge of English in written and spoken form

Our Offer:

  • International, interdisciplinary working environment on an attractive research campus, ideally situated between the cities of Cologne, Düsseldorf, and Aachen
  • A comprehensive further training programme, including German language courses
  • Flexible working hours and various opportunities to reconcile work and family life
  • Limited for 5 years with possible longer-term prospects
  • Full-time position with the option of slightly reduced working hours
  • Salary and social benefits in conformity with the provisions of the Collective Agreement for the Civil Service (TVöD).


Forschungszentrum Jülich aims to employ more women in this area and therefore particularly welcomes applications from women.

We also welcome applications from disabled persons.

Additional Information

We look forward to receiving your application, preferably online via our online recruitment system on our career site, quoting the above-mentioned reference number.

Contact
Judith Dresen
Telefon: +49 2461 61 9700