DRESDEN-concept Career Offers

Description of the PhD topic (subproject A7- Reinforcement learning for mode choice decisions): This PhD project will develop and implement a Deep Reinforcement Learning (DRL) model for dynamic mode choice within the MATSim agent-based transport simulation framework. The main task is to enable simulated agents to choose transportation modes, such as car, bus, bike, or walking, based on real-time feedback from the environment, including traffic conditions, travel time, and cost. The project will define the DRL components (states, actions, rewards, policies), select and implement suitable DRL algorithms, and integrate them into MATSim. It will involves building realistic test scenarios, running simulations, and progressively refining agent learning strategies using techniques like curriculum learning and reward shaping. The DRL model will be evaluated in various transport policy scenarios to analyze system-level impacts on travel behavior and to support sustainable mobility planning within the AgiMo digital twin framework. The project will actively collaborate with other AgiMo subprojects.
Tasks: Independent and cooperative qualification through scientific research within the project; training in the technical tasks of the individual dissertation topic through study of the literature and in making the objectives more precise; working on the individual PhD study project with its focus on Reinforcement learning for mode choice decisions in collaboration with other CRC members (fellow students and supervising professors); implementation of the planned research program, evaluation and interpretation of the results, elaboration and presentation of the research; participation in lectures, workshops and summer schools according to the guidelines of the RTG curriculum; supporting scientific graduation work (Bachelor/Master/Diploma) in the subject-specific research field; regular reporting on research progress to the supervising professors; publishing the results of the research work individually and in concert with others; cooperative maintenance of internal exchange platforms (database, information pages, etc.); summarizing the results of the individual doctoral study project in a dissertation within the due time of 3 years and 9 months. Successful candidates will work together with approx. 7 researchers at the Chair of Econometrics and Statistics esp. in the Transport Sector and the reinforcement learning Dresden (rl-dresden.de) group and together with the other universities and chairs being part of the CRC.

excellent, very good or good university degree (diploma, master's degree) in transport engineering or civil/electrical/control engineering or mathematics or related study programs with a solid basis in choice modelling and/or reinforcement learning, with knowledge of MATSim is advantageous.

General Requirements: We are looking for first-class graduates with expertise in the CRC-addressed PhD subjects, high interdisciplinary desire to learn and willingness to cooperate, openness for internationalization and diversity, very good verbal and written English communication skills as well as the absolute determination to submit the dissertation after 3 years and 9 months of research.

What we offer:

• Pioneering Research Environment: Shape the future of data-driven transport planning and management through the involvement in collaborative research.
• Cross-Disciplinary Collaboration: Immerse yourself in a highly collaborative and interdisciplinary research environment, where you'll work alongside experts from fields such as transport and urban planning, engineering, data science, computer science.
• Skill Development: Our extensive qualification concept goes beyond research, offering targeted training in research methods, project management, and leadership skills. This ensures you graduate not only as a specialist in your field but also as a well-rounded professional.
• Global Networking: Collaborate with our network of local and international partners, fostering connections that transcend geographical boundaries and enrich your academic and professional network. This includes a paid research stay abroad for three months.
• Career Advancement: Receive dedicated support for fellowship applications and tailored guidance for your career.
• Quality of Life in Dresden: Experience a high quality of life in Dresden, with its dynamic urban scene, relatively affordable living, rich cultural offerings, and vibrant nightlife.
  Further questions regarding the open PhD position can be discussed with the supervisor, Prof. Dr. Ostap Okhrin (ostap.okhrin@tu-dresden.de).
  TUD strives to employ more women in academia and research. We therefore expressly encourage women to apply. The University is a certified family-friendly university. We welcome applications from candidates with disabilities. If multiple candidates prove to be equally qualified, those with disabilities or with equivalent status pursuant to the German Social Code IX (SGB IX) will receive priority for employment.
  Please submit your detailed application including a cover letter detailing your research interests stating the job-ID “TRR408-A7” along with your curriculum vitae, academic transcripts with marks, a letter of recommendation and your publications (if applicable) by August 7, 2025 (stamped arrival date of the university central mail service or the time stamp on the email server of TUD applies), preferably via the TUD SecureMail Portal https://securemail.tu-dresden.de by sending it as a single PDF-file to ostap.okhrin@tu-dresden.de or to: TU Dresden, TRR 408, Prof. Dr. Ostap Okhrin, Helmholtzstr. 10, 01069 Dresden, Germany. Please submit copies only, as your application will not be returned to you. Expenses incurred in attending interviews cannot be reimbursed.

Reference to data protection: Your data protection rights, the purpose for which your data will be processed, as well as further information about data protection is available to you on the website: https://tu-dresden.de/karriere/datenschutzhinweis.