Position 1 : David Cornu (2020-2022)


Position  at LERMA, Observatoire de Paris 

Email : philippe.salome@obspm.fr, cyril.tasse@obspm.fr, stephane.aicardi@obspm.fr
Object : MINERVA Application

The Observatoire de Paris is seeking candidates for a 2-years position at LERMA on Machine Learning for Radio-astronomical 2D images and 3D data cubes. The position is no longer open.

Organization: LERMA, Observatoire de Paris
Street Address : 61 Av. de l’Observatoire
City: Paris
Zip/Postal Code: 75014
Country: France

The position is open within the MINERVA project (Machine Learning for Radioastronomy at Observatoire de Paris. This project federates astrophysicists interested in a variety of astrophysical phenomena. https://vm-wordpress-lerma01.obspm.fr/minerva/

Radioastronomy is experiencing an explosion of volumes of observational data with the development of giant interferometers (LOFAR, ALMA, NenuFAR, SKA). These instruments produce huge and numerous two and three-dimensional datasets (2D-spatial and one spectral (ie velocity) coordinates). Faced to these daily TB-scale data (PB-scale with SKA), the traditional methods of source detection and classification reach their limits. In parallel, machine learning methods have undergone algorithmic developments that bring them to a high level of maturity.

The goal of this project is to perform pilot implementation of new methods for (i) radio sources classification based on their morphology, (ii) multi-wavelength cross identification and (iii) shape recognition and analysis in radio-astronomical large data-cube.

The successful candidate will carry out an inventory of existing methods and design new tools that shall be applied to large 2D-planes/datacubes and to large quantities of such data.

MINERVA will make use of datasets from ALMA and LOFAR. The new algorithms will also be tested in the context of the SKA data challenges.

Applicants should have at least an engineer diploma in the field of Machine Learning or a PhD in physics, astronomy, or computer science by the time of the appointment. Experience in Astronomy is not mandatory. We encourage applications from candidates with a strong expertise in either the manipulation or the development of state-of-the-art Machine Learning methods. Experience with manipulating images and data cubes will also be considered. Skills in one or several programmation languages (e.g. Python, Fortran, C++) are necessary.

The successful candidate will have access to computing ressources dedicated to MINERVA (a dedicated server with GPUs).

The LERMA/Observatoire de Paris maintains a lively visitor program and hosts regular workshops and conferences throughout the year. The successful candidate will be immersed in an internationally visible research environment in the Paris Campus, with rich intellectual and computational resources.

The appointment is for 2 years with a salary including French social security benefits. Funding will also be allocated for travel.

Applicants should submit a CV (max. 2 pages), a publication list, a short review of previous works (2 pages) and a statement of research interests (2 pages). Applications should be sent via email (see above).

For full consideration materials must be received before October 31st, 2019.

Included Benefits: French national medical insurance, Maternity/Paternity leave, Lunch subsidies, Family supplement for children, Participation to public transport fees, Pension contributions