We have an exciting opportunity for a postdoctoral research assistant with expertise in computational statistics and statistical machine learning to join our team (Professor Chris Holmes and Professor Arnaud Doucet) to work on the development of new Bayesian theory and scalable methods for causal analysis of large observational (longitudinal) data sets arising from medical and health related studies. This includes work in Bayesian nonparametric learning and Monte Carlo methods for inference. As the postdoctoral research assistant, you will conduct original research and develop and implement novel scalable schemes for causal inference and learning. You will develop theoretical and empirical frameworks for analysing the developed methodologies and manage your own academic research. The post is funded by the Bayes4Health EPSRC programme grant and the postholder will have the opportunity to interact with other researchers on this programme as well as member of the Computational Statistics and Machine Learning group in the Department of Statistics in Oxford.
You must hold a PhD/DPhil, or be close to the completion of, in applied probability, computer science, statistics or an affiliated discipline. You must have significant relevant experience in the development and study of inference and learning schemes and be able to collaborate effectively with PIs and project partners. You will have the ability to supervise the research of DPhil students or junior researchers. Experience in one or more of the following areas is desirable: causal inference/causal machine learning, latent variable models, learning theory, PAC-Bayes, statistical machine learning, variational methods.
This post is fixed-term for 2 years, in the first instance.
Only applications received before 12.00 midday on 22 June 2020 will be considered. Interviews will be held on 6 July 2020.