Postdoc in Machine Learning Techniques for Communication over the Fiber-Optic Channel

Applications are invited for a 2-year postdoctoral research position funded by the Villum Foundation Synergy: ‘Machine learning-enabled fiber-optic communication (MARBLE). The objective of the MARBLE project is to develop novel machine learning based strategies for communication over the nonlinear optical fiber channel. The start date is flexible, but preferably before April 1, 2022.

The project is interdisciplinary and will cover topics within the field of machine learning and optical communication. The project will be carried out in Machine Learning in Photonic Systems (M-LiPS), group. The group has a strong track record and industry collaboration in the application of machine learning techniques to optical communication systems and photonic systems in general.

The project will explore the latest advances within machine learning to enable nonlinear-distortion free communication over the optical fibre channel. It will be explored how to combine machine techniques with optical communication, to enable spectrally efficient and robust  optical communication systems covering ultra-wide band transmission (O+E+S+C+L band). More specifically, the application and efficient training for auto-encoders will be investigated.  The project will cover both algorithm development as well as experimental implementations.   

Responsibilities and qualifications
The candidate will be focusing on improving communication strategies over the nonlinear fiber optic channel using machine learning. Moreover, the candidate will participate in implementing the developed techniques in experimental test-bed and performing transmission experiemnts. 

This position will investigate the research topics below using both theoretical and experimental methods:

• Gradient-free training of neural networks
• Development of novel machine learning based transmitter and receiver schemes for ultra-wideband optical communication systems
• Investigation of the impact of the components non-idealities on the devised machine learning based communication strategies
• On-line training of transmitter and receiver architectures

As a formal qualification, you must hold a PhD degree in telecommunication, machine learning, photonics engineering or equivalent.

Moreover, the candidate shall have experience with one or more of the following skills:

• Optical or digital communication systems
• Machine learning techniques such as: neural networks, Bayesian filtering, reinforcement learning, evolutionary algorithms, numerical optimization
• Experimental realization of high-speed optical communication systems employing advanced modulation formats and coherent detection
• Python/PyTorch/TensorFlow/MATLAB
• Ability to work independently, to plan and carry out complicated tasks
• Excellent communication skills in English, both written and spoken
• Innovative skills and the ability to generate new ideas
• Experience in student supervision at B.Sc., M.Sc. and Ph.D. levels

Assessment
In the assessment of the candidates, consideration will be given to

• Publications at leading conferences and journals within the field of optical/digital communication/machine learning
• Invited conference and journal papers
• Overall research experience
• International experience
• Internal and external collaboration
• Communication skills
• Experience with software for version control such as git

We offer
DTU is a leading technical university globally recognized for the excellence of its research, education, innovation and scientific advice. We offer a rewarding and challenging job in an international environment. We strive for academic excellence in an environment characterized by collegial respect and academic freedom tempered by responsibility.

Salary and terms of employment
The appointment will be based on the collective agreement with the Danish Confederation of Professional Associations. The allowance will be agreed upon with the relevant union. The period of employment is 2 years.

You can read more about career paths at DTU here.

Further information
Further information may be obtained from Professor Darko Zibar (dazi@fotonik.dtu.dk).

You can read more about DTU Fotonik at www.fotonik.dtu.dk/english. 

If you are applying from abroad, you may find useful information on working in Denmark and at DTU at DTU – Moving to Denmark.

Application procedure
Your complete online application must be submitted no later than 1 March 2022 (Danish time). Applications must be submitted as one PDF file containing all materials to be given consideration. To apply, please open the link "Apply online", fill out the online application form, and attach all your materials in English in one PDF file. The file must include:

• Application (cover letter)
• CV
• Academic Diplomas (MSc/PhD)
• List of publications

Applications received after the deadline will not be considered.

All interested candidates irrespective of age, gender, disability, race, religion or ethnic background are encouraged to apply.

DTU Fotonik has 220 employees with competences in optics and is one of the largest centers in the world based solely on research in photonics. Research is performed within communication technology, ultra-high speed optical transmission systems, optical sensors, lasers, LEDs, photovoltaics, bio-photonics, nano-optics and quantum communication and photonics. 

Technology for people
DTU develops technology for people. With our international elite research and study programmes, we are helping to create a better world and to solve the global challenges formulated in the UN’s 17 Sustainable Development Goals. Hans Christian Ørsted founded DTU in 1829 with a clear vision to develop and create value using science and engineering to benefit society. That vision lives on today. DTU has 12,900 students and 6,000 employees. We work in an international atmosphere and have an inclusive, evolving, and informal working environment. DTU has campuses in all parts of Denmark and in Greenland, and we collaborate with the best universities around the world.