PhD position on probabilistic programming for Bayesian machine learning

This 4-year PhD position is embedded in the Signal Processing Systems group of the Electrical Engineering department of Eindhoven University of Technology, the Netherlands. The position is part of an ongoing research program to develop intelligent agents by probabilistic (i.e., Bayesian) machine learning methods. Typical applications for these agents include in-situ control of extended reality algorithms, self-driving vehicles and adaptive robotics. A core aspect of the research program focuses on automating probabilistic inference agents through message passing algorithms on graphical dynamic models. In the computer science literature, this style of programming is called Probabilistic Programming (PP). In our team, we develop an efficient PP toolbox (in Julia:

http://julialang.org

) to support real-time and online simulation of these Bayesian agents in IoT and wearable devices. 

This PhD project is aimed at further development of both the theory and practice of probabilistic programming methods for message passing-based inference in graphs. Key areas of interest include Bayesian machine learning, functional and reactive programming, probabilistic graphical networks and automatic differentiation. The position is very suited for a strong software developer with a serious interest in learning about modern developments in Bayesian machine learning and probabilistic programming. 

In case this recruitment ad sparks your interest, please watch the following presentation (Beyond Deep Learning: Natural AI Systems) to learn more about our lab's research goals: https://youtu.be/QYbcm6G_wsk . Please also browse our web page http://biaslab.org for more information on our research lab.