For any questions, do not hesitate to ask:
Dr. Nico Hoffmann Tel.: +49 351 260 3668
Place of work:
31 July 2022
The HZDR is committed to equal opportunity employment and we strongly encourage applications from qualified female candidates. We also carefully consider all applications from job candidates with severe disabilities.
Bautzner Landstraße 400
Postdoc (f/m/d) Inverse Problems/Imaging/Optimisation
Through cutting-edge research in the fields of ENERGY, HEALTH and MATTER, Helmholtz-Zentrum Dresden-Rossendorf (HZDR) solves some of the pressing societal and industrial challenges of our time. Join our 1.400 employees from more than 50 nations at one of our six research sites and help us moving research to the next level!
Hoffmann lab at the Institute of Radiation Physics is researching machine learning based digital twins of laser-driven plasma accelerators contributing to our fundamental research about theory, experimental validation and automatic control of this system enabling promising applications like next generation X-ray light sources. More details about our research can be found here: https://photon-ai-research.github.io
You will be researching machine learning methods that are solving inverse problems encountered by our experimentalists. From a mathematical perspective, you will be dealing with the phase problem which is quite prominently encountered in analysis of X-ray diffraction data that we are collecting at our HIBEF instrument at EuropeanXFEL. You will be designing method that integrate information from many orthogonal observations of the system’s state, incorporate prior knowledge about physical processes while being robust to out-of-distribution data. You will be also coordinating your efforts with all involved parties to stimulate fast integration of your code into experiment at HZDR as well as EuropeanXFEL.
Does that sound interesting to you as a Physicist, Mathematician or Computer Scientist? Then submit your applications as Postdoc (f/m/d) Inverse Problems/Imaging/Optimisation as soon as possible.
The position will be available from 1 August 2022. The employment contract is limited to 31 December 2023 but extensions will be possible upon success.
- Research and implementation of ML-assisted algorithms for solving ill-posed inverse (imaging) problems
- Proactive collaboration with experimentalists (f/m/d) at HZDR and EuropeanXFEL (Link) to translate knowledge and requirements for data acquisition and in-situ data analysis into experiment
- Publication of papers in high-quality journals in Physics, Mathematics and Machine Learning conference
- (Joint) supervision of PhD and Master's students (f/m/d) working on inverse problems
- Contribution to teaching basics of inverse problems and ML at university
- Actively collaborating with industry, academia, government labs, and applications developers in a variety of venues
- PhD degree in Computational Physics, Mathematics, Computer Science or a closely related discipline
- Good mathematical background (e.g. linear algebra, statistics, optimisation)
- Preferably proven knowledge in solving ill-posed inverse problems (e.g. phase retrieval) and in analysis/reconstruction of X-ray imaging modalities (e.g. SAXS, Holography Ptychography)
- Good programming skills in Python
- Proven knowledge of PyTorch is a strong plus
- Publication record in computational imaging, inverse problems, and/or machine learning
- Interested in Plasma Physics, inverse problems, phase retrieval, Machine Learning, Image Analysis and Deep Generative Models
- A vibrant research community in an open, diverse and international work environment
- Scientific excellence and extensive professional networking opportunities
- The employment contract is limited to to 31 December 2023 but extensions will be possible upon success
- Salary and social benefits in accordance with the collective agreement for the public sector (TVöD-Bund) including 30 days of paid holiday leave, company pension scheme (VBL)
- We support a good work-life balance with the possibility of part-time employment and flexible working hours
- Numerous company health management offerings
- An employer subsidy for the VVO job ticket
Kindly submit your completed application (including cover letter, CV, diplomas/transcripts, etc.) only via our Online-application-system.