Open Positions

For semester, masters, and internship projects visit the ‘Teaching and Projects’ section.

Postdoctoral Position in Deep Learning
Applied to Optical Imaging

The Laboratory of Optics (LO) at EPFL has a postdoctoral opening for the study of optical imaging using deep learning techniques. Learning techniques opens many new research opportunities in optical imaging and several groups have joined the community. Recent studies, from our group and also others, have demonstrated the potential of using neural networks for improving the reconstructions.

The postdoctoral scholar will develop numerical algorithms based on learning theory to optimize the solution considering different types of prior information. The work will be carried out in collaboration with PhD students in LO working on simulations and experiments.

Requirements

  • PhD degree in computer sciences or engineering.
  • Solid background in deep learning techniques.
  • Strong interest and experience in teamwork, supervision of graduate students, and project coordination.
  • Previous experience in optics, vision, or imaging is an asset.
  • Proficiency in written and spoken English.

Offer

  • Access to world class research facilities.
  • Entering a dynamic and diverse team of highly motivated students and scientists doing research in an interdisciplinary field.
  • A full-time contract for a period of two years with the possibility for extension.
  • A competitive salary (>80,000 CHF yearly gross).

The start date for this position is January 1st, 2018. If interested, please send your application package including a cover letter and a CV with publications and referees lists to: info.lo@epfl.ch.

Relevant publications from our group

[1] U. S. Kamilov, I. N. Papadopoulos, M. H. Shoreh, A. Goy, C. Vonesch, M. Unser, and D. Psaltis, “Learning approach to optical tomography,” Optica, vol. 2, no. 6, pp. 517–522, 2015.

[2] U. S. Kamilov, I. N. Papadopoulos, M. H. Shoreh, A. Goy, C. Vonesch, M. Unser, and D. Psaltis, “Optical tomographic image reconstruction based on beam propagation and sparse regularization,” IEEE Transactions on Computational Imaging, vol. 2, no. 1, pp. 59–70, 2016.

[3] J. Lim, A. Goy, M. H. Shoreh, M. Unser, and D. Psaltis, “Assessment of learning tomography using Mie theory,” arXiv:1705.10410, 2017.