Postdoc in Deep Generative Models for Stochastic Optimization – DTU Management

Skip to main content.

• Profile
• Sign Out

View More Jobs
Postdoc in Deep Generative Models for Stochastic Optimization – DTU Management
Kgs. Lyngby, Denmark
Job Description

We are looking for an ambitious candidate for a PostDoc project to focus on deep generative models used in stochastic optimization.
You will be responsible for developing Deep Generative Models (DGMs) based on Variational Autoencoders, Normalized Flows, etc., that are able to generate realistic scenarios to be used in stochastic optimization. Furthermore, you will be working on a framework that makes it possible to generate a small set of scenarios that reflects all the main properties of the full scenario space.
As part of the project, you will implement and test algorithms, and further develop your skills in writing scientific papers.
Research area and project description
Many important decisions with significant implications for the future of our societies are taken under uncertainty, without a full picture of how the different variables the decisions are based on will change over time. For example, the ongoing green transition requires large and urgent societal investments in new energy modes, infrastructure and technology. But the decisions span over a long time-horizon, and there is high uncertainty about future energy prices and demand, and the capacity of renewable resources to replace fossil fuels. 
Several classical mathematical tools are used to support decision making under uncertainty, including stochastic optimization and robust optimization. However, with these traditional models it can be difficult to solve optimization problems defined on a large number of scenarios. This means that generally only a small set of scenarios is considered, leading to less well-founded decisions.
In the ERC-funded DECIDE project we will completely rethink the way complex stochastic optimization problems are solved. Instead of solving them based on a fixed set of forecasted scenarios, we will use an iterative process that allows us to generate a palette of near-optimal solutions. Knowing the full spectrum of possible choices enables a much broader discussion of investments, leading to a more transparent and inclusive decision process. The developed models will be tested on data from energy investment models, as well as transport infrastructure problems.
You will join a strong academic team at DTU Management’s Management Science division. Three PhD students and four PostDocs will work on the project, as well as several international experts in operations research.
The project is headed by Professor David Pisinger who has published several papers in the field supervised more than 30 PhD students.
DECIDE is funded by the European Research Council (ERC-2022-ADG).
Responsibilities and qualifications
As part of the DECIDE project you will be working on developing next generation of tools for decision making under uncertainty. You must: 

• Have experience in Deep Generative Models (e.g. Variational Autoencoders, Normalized Flows, Generative Adversarial Networks)
• Have knowledge about implementation of metaheuristics.
• Have some knowledge about stochastic optimization.
• Be passionate for research and for pushing the scientific frontiers.
• Have excellent programming skills.
• Possess good collaboration skills.
• Be fluent in English, spoken as well as written.

As a formal qualification, you must hold a PhD degree (or equivalent). 
It would be an advantage to have knowledge about efficient algorithm and solution of optimization problems.
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 3.5 years (42 months). Starting date is 1 May 2024 (or according to mutual agreement). The position is a full-time position.
You can read more about career paths at DTU here .
Further information 
Further information may be obtained from Professor, David Pisinger (DTU), tel.: +45 4525 4555, email: [email protected] . 
You can read more about DTU Management at www.man.dtu.dk . 
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 8 March 2024 at 23:59 (Danish time). Applications must be submitted as one PDF file containing all materials to be given consideration. To apply, please open the link "Apply now", 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 – in English)
• List of publications 
• A research statement (2-3 pages) explaining your ideas and relevant literature.

Applicants not providing all the above material will not be considered.
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.
About us 
DTU Management conducts excellent research in the intersection between management, technology and economics. We develop solutions in close cooperation with companies and public authorities. Our research aims at strengthening welfare, productivity, and sustainability within society. A key element is the role of technology and its interaction with industry and individuals. The department is divided into four divisions: Technology & Business Studies, Management Science, Climate & Energy Policy and Transportation Science. The department offers a wide range of courses and programs at bachelor, master and PhD level across DTU’s study programs. The department has around 200 employees, with around half coming from abroad.  
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 mission to develop and create value using science and engineering to benefit society. That mission lives on today. DTU has 13,500 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.

Apply Now
Job Info

• Job Identification 3035
• Job Category VIP B
• Posting Date 01/18/2024, 06:14 AM
• Apply Before 03/08/2024, 05:59 PM
• Locations Produktionstorvet, Kgs. Lyngby, 2800, DK

Similar Jobs

• 
  PhD scholarship in Diversifying Heuristics for Stochastic Optimization Problems – DTU Management
  Kgs. Lyngby, Denmark Posted on 01/18/2024
  

  We are looking for an ambitious candidate for a PhD project to focus on development of heuristics for stochastic optimization. You will be responsible for developing fast heuristics or MIP-models for solving two-stage optimization problems, such that many alternatives can be investigated. You should be an experienced programmer, knowing how to write efficient algorithms.

  
  
  
• 
  Postdoc in Modelling and Optimization of Carbon Capture Processes - DTU Chemical Engineering
  Kgs. Lyngby, Denmark Posted on 02/22/2024
  

  Centre for Energy Resources Engineering (CERE) at DTU Chemical Engineering is seeking a postdoctoral researcher to contribute to our CO2 capture research in the project “Optimizing carbon capture simulation through advanced modelling tools—CapSim.”

  
  
  

Page Postdoc in Deep Generative Models for Stochastic Optimization – DTU Management - DTU Career Site Careers loaded

Skip to main content.
American English Dansk American English

I am an employee
 
Skip to main content.
Are You Still With Us?
It seems you've been gone for a while. For security reasons we will end your session automatically in 03:00 unless you would like to continue working.
End Session Continue Working
 
Skip to main content.
Work Summary

This summary is generated by AI Assist. Click inside the summary text box to make changes as necessary.

Discard Add Summary