A postdoctoral position in machine learning in computational physical

chemistry is open in the group of Prof. Bjørk Hammer at Aarhus University.

The starting date is preferably around January 2018. Duration of the

employment may be from one to three years.

Applicants must hold a PhD degree in physics, chemistry, nano-science,

or computer science (or equivalent). Previous experience with machine

learning methods and/or first principles energy calculations in

physical chemistry is required. Experience with programming in python

is highly desired.

In the position, the successful candidate will identify and develop

machine learning techniques that may speed up first principles

calculations of equilibrium structures and reaction pathways in

physical chemistry. Presently, the group is working with unsupervised

clustering techniques (see:

http://pubs.acs.org/doi/abs/10.1021/acs.jctc.6b01119), and with

supervised kernel ridge regression and artificial neural network

methods. The latter methods are for instance used to assign local

atomic energies that are otherwise not available within the first

principles calculational framework.

Interested applicants should send their expression of interest

(motivation letter, CV, contact info for up to three references) by e-mail

to Bjørk Hammer ([email protected]). Please use as e-mail subject:

"postdoctoral application 314".