About the position
Job description ICAI Robust RAIL Lab is looking for a postdoctoral researcher to help bridge that gap, along two connected directions. Job description The Dutch railway network is approaching its capacity limits, and the timetable that keeps it running is one of the most consequential optimization problems in the country — spanning many orders of magnitude in detail, from macroscopic capacity-planning down to millisecond-level microscopic simulation. No single algorithm spans that whole range on its own. ICAI Robust RAIL Lab — a joint initiative of TU Delft, Utrecht University, and NS/ProRail under the NWO LTP-ROBUST programme — is looking for a postdoctoral researcher to help bridge that gap, along two connected directions. Trustworthy multi-model optimization. Combine models at different levels of abstraction — macroscopic capacity planning, mesoscopic scheduling, microscopic simulation — into a single, computationally tractable pipeline, without sacrificing trust in the result. Draw on recent work on self-certifying optimization proxies — fast machine learning surrogates that carry their own provable optimality guarantee, falling back to an exact solver only on the instances that need it — and on the broader idea of building a relaxation that's fine-grained exactly where a query needs it and coarse elsewhere. This hybrid, multi-model philosophy motivates decision support in other domains as well. Timetabling for a multi-operator railway. ProRail's system for allocating rail capacity is shifting from an operator-request model to one where train paths are effectively "sold" to multiple, competing railway operators — turning capacity allocation into a genuine market-design problem. How do you allocate scarce train paths fairly, efficiently, and strategy-proofly across operators who each hold private information about their own needs? This is a live mechanism-design question, not a hypothetical one: it echoes the FCC's landmark two-sided spectrum incentive auction. You'll work with researchers in the Algorithmics section, headed by Mathijs de Weerdt, contacts at ProRail and NS, and some of the lab's researchers (PhD tracks on hub planning, real-time rescheduling, crew rostering, energy-efficient operation) — with freedom to shape your own research agenda within this scope. What we offer: a postdoctoral position for 16 fte months (working days per week and exact duration negotiable), embedded in a well-resourced, industry-connected lab. Job requirements We're looking for: a recent PhD graduate in optimization, operations research, machine learning, or a closely related field, with strong mathematical/algorithmic grounding and a genuine interest in working at the interface of theory and a large, real-world system for sustainable transport. Conditions of employment Duration of contract is 16 months. Temporary. A job of 32-40 hours per week. Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities. An excellent pension scheme via the ABP. The possibility to compile an individual employment package every year. Discount with health insurers on supplemental packages. Flexible working week. Every year, 232 leave hours (at 38 hours). You can also sell or buy additional leave hours via the individual choice budget. Plenty of opportunities for education, training and courses. Partially paid parental leave Attention for working healthy and energetically with the vitality program. Will you need to relocate to the Netherlands for this job? TU Delft is committed to make your move as smooth as possible! The HR unit, Coming to Delft Service , offers information on their website to help you prepare your relocation. In addition, Coming to Delft Service organises events to help you settle in the Netherlands, and expand your (social) network in Delft. A Dual Career Programme is available, to support your accompanying partner with their job search in the Netherlands. .
This listing was collected from a public source and is reproduced here for
information only. Always confirm the details on the original posting before applying.
View the original posting