What you'll do
- Design and develop discrete-event simulations using SimPy to model logistics chains, maintenance workflows, and operational bottlenecks across platform types.
- Build and solve optimisation models in IBM CPLEX to address scheduling, resource allocation, and planning challenges in real defence scenarios.
- Analyse high-volume sensor data from air, land, and sea platforms to extract signals, detect anomalies, and engineer features for predictive modelling.
- Validate models with domain experts, test their sensitivity to assumptions, and communicate uncertainty, trade-offs, and limitations to operational users.
- Write clean, modular Python code and work with data engineers, full-stack developers, and domain experts to move models from prototype into production.
- Contribute to internal tooling and knowledge-sharing so the team's analytical capabilities grow alongside yours.
What success looks like
Initially: you understand the operational context, the available data, and the real constraints — and you are already challenging assumptions alongside subject-matter experts.
As you take ownership: the simulation models reflect real operational constraints, not textbook ones. Optimisation models produce schedules and resource plans that practitioners recognise as usable, not just mathematically correct. Sensor pipelines you've built or improved are stable, tested, and easier for the next person to extend.
Over time: your ownership expands from individual models to the analytical patterns the whole team reaches for — tested, reusable, and faster for everyone.
What you bring
- Approximately five years of relevant applied experience in data science, operations research, or a closely related field — or equivalent depth through a PhD, industrial research, or another technically intensive pathway.
- Strong Python engineering skills, including modular design, automated testing, version control, and experience taking analytical code into production or production-like environments — with hands-on use of pandas, NumPy, and scikit-learn.
- Deep applied experience in at least two of the following: discrete-event simulation (SimPy preferred and in use here, though comparable tools transfer), mathematical optimisation (IBM CPLEX is the solver in use; Gurobi, OR-Tools, Pyomo, and other backgrounds are welcome), and sensor or time-series modelling (turning high-frequency, high-volume streams into reliable analytical outputs). You should be able and willing to contribute across the third area.
- Ability to translate ambiguous operational questions into concrete analytical approaches; comfortable working from messy real-world problems, not just well-specified ones.
- Professional working proficiency in Dutch and English; both are used day to day in technical discussions, documentation, and collaboration with domain experts.
- Eligibility to obtain and maintain the required national or NATO security clearance for this role. ILIAS Solutions supports candidates through the clearance process and is happy to explain what is involved before you apply.
Clearance eligibility, professional Dutch and English, and strong applied Python modelling experience are essential. We do not expect equal depth in simulation, optimisation, and sensor analytics — strong candidates may be deeper in two areas and ready to grow in the third.
Nice to have
- Background in logistics, maintenance planning, systems engineering, or defence operations; familiarity with the domain problems makes the modelling work faster and more credible.
- Experience packaging analytical components with Docker or comparable container technology.
- Experience processing large datasets with Spark, PySpark, or comparable distributed-data tools.
- Exposure to digital twins, operational dashboards, or predictive maintenance applications.
- Prior work in secure or regulated environments — defence, aviation, or similar.
