Job Description
About this position
Factories used to be pretty straightforward. Henry Ford once famously said: “any customer can have a car painted any color they want as long as it’s black”. Not anymore. Modern factories are interrelated and stochastic. Parallel processes depend on each other, custom jobs of custom sizes come at different times, and failed processes and reallocation of work cause cumulative delays. Together, these factors determine the risk (probability) of overshooting agreed delivery times. Making a workflow robust to disruptions is done by introducing slack, but that comes at the cost of reduced efficiency. By reasoning with uncertainty about cascaded effects, we can balance efficiency with robust delivery. In this project, you will use state-of-the-art probabilistic programming and model-based reinforcement learning techniques to optimize factory workflows under uncertain, interrelated and cascading events.
What will be your role?
...Apply for this Position
Ready to join TNO? Click the button below to submit your application.
Submit Application