Research Fellows within Bayesian Inference for Medical Applications

Aalto University - Sensor Informatics and Medical Technology Research Group

The Sensor Informatics and Medical Technology research group focuses on the development of  probabilistic (i.e. Bayesian) signal processing and machine learning methods especially for health and medical applications. Other applications include smartphone sensor fusion, robotics, positioning systems, target tracking, and many other indirectly measured systems. 

We are looking for 

Research Fellows within Bayesian Inference for Medical Applications 

The positions will be appointed for a fixed term appointment starting in late 2017 or early 2018. 

The position is available in the growing Sensor Informatics and Medical Technology research group. We aim to carry out original high-quality research and continuously publish in top journals and conferences of the field. We have an extensive international collaboration network, which will facilitate the mobility of our researchers to leading research groups abroad, and vice versa. Our group is located at the Department of Electrical Engineering and Automation at Aalto University. 

Possible research topics include: 

  • Bayesian filtering and machine learning methods for automated diagnosis of cardiac diseases. Promising methods have been, for example, Kalman filters and Gaussian process classifiers, deep models could also be used.
  • Sensor fusion methods for motion tracking and positioning. The used sensors include, e.g., inertial and magnetic sensors, and the methodology typically includes non-linear Kalman filters and particle filters along with methods like MCMC.
  • New computational methods and models for highly non-linear and non-Gaussian spatio-temporal stochastic systems. This kind of methods can be based on, for example, nonlinear Kalman-type of methods, expectation-propagation, posterior-linearization, EP, sigma-point methods, or sequential Monte Carlo.
  • New computational methods and models for machine learning for signal processing. Examples of such methods and models are state-space GP methods, SPDE methods for GPs as well as hierarchical / deep models, probabilistic programming languages, graphical methods etc. 

Persons hired are expected to participate in the supervision of students and teaching following the standard practices at the department. 

Applicants are expected to have an excellent research track record in Bayesian filtering, probabilistic machine learning and/or the application fields. Good command of English, doctoral degree and a good academic publication record are necessary prerequisites. 

Research fellow applicants are expected to have in addition external experience as postdoc or equivalent experience from industry and teaching portfolio. 

Compensation, working hours and place of work
The salary will be negotiated case-by-case, depending on experience and qualifications. The contract includes occupational health benefits. 

How to apply
Please send your application in a single PDF file through the electronic recruitment system (link: no later than October 31, 2017. Early submission is strongly encouraged, as applications will be processed and evaluated upon arrival. Include your CV, list of publications, and names and contact information of two senior academics willing to give more information. 

Further information
HR Coordinator, Ms. Jaana Hänninen, e-mail "" (application process, practical arrangements).

Professor Simo Särkkä, e-mail "" (research related information)

Share this job
  Share by Email   Print this job   More sharing options
We value your feedback on the quality of our adverts. If you have a comment to make about the overall quality of this advert, or its categorisation then please send us your feedback
Advert information

Type / Role: