A postdoc position is open for a project within BiGmax, the highly interdisciplinary Max Planck research network. The project is in collaboration between the NOMAD Laboratory at the Fritz Haber Institute and Humboldt University Berlin and the Max Planck Institute for Iron Research in Düsseldorf (group Advanced Transmission Electron Microscopy) and aims at developing a novel deep-neural-network (DNN) based tool for the automatic analysis of scanning-transmission-electron-microscopy (STEM) images, with a focus on identifying the local lattice symmetries, atomic site occupation, order-disorder and defect structures. The projects build on recent breakthroughs from both participating groups in the characterization of grain boundaries in elemental metals [1] and the development of deep-learning-based structure-recognition tools [2,3].

The position,which will be hosted at the NOMAD Lab in Berlin, is for 1 year, starting asap but not later than April 2022.

Together with an outstanding materials-science research curriculum, strong scientific-programming skills and experience in data mining are required.

The interested candidates should apply to Dr. Luca Ghiringhelli ([email protected]) providing a motivation letter, scientific CV, including 3 contact persons for a reference letter, and an essay of the programming skills (e.g., a project on github).

[1] Meiners, Thorsten, Timofey Frolov, Robert E. Rudd, Gerhard Dehm, and Christian H. Liebscher. "Observations of grain-boundary phase transformations in an elemental metal." Nature 579, no. 7799 (2020): 375-378.

[2] Ziletti, Angelo, Devinder Kumar, Matthias Scheffler, and Luca M. Ghiringhelli. "Insightful classification of crystal structures using deep learning." Nature communications 9, no. 1 (2018): 1-10.

[3] Leitherer, Andreas, Angelo Ziletti, and Luca M. Ghiringhelli. "Robust recognition and exploratory analysis of crystal structures via Bayesian deep learning." Nature communications, in press. arXiv preprint arXiv:2103.09777 (2021).