Postdoctoral fellow in machine learning with epidemiological applications - Hiring in process/Finished, not possible to apply

The Computational Biology & Biological Physics group pursues research in the fields of computational biology and machine learning, using a broad set of models and methods, often rooted in statistical and computational physics. In particular, the group develops machine learning techniques for biomedical and healthcare applications, computational models for biomolecular and cell systems, and methods for large-scale analysis of spectroscopic and imaging data on biological processes. 

The research is genuinely cross-disciplinary in character, and often undertaken in collaboration with groups from other areas. The Computational Biology & Biological Physics group has an opening for a two-year postdoctoral fellow in machine learning with a focus on epidemiological applications, starting in April 2022, or by agreement.

Introduction 
The Computational Biology & Biological Physics group is engaged in a number of cross-disciplinary projects where machine learning methods are being developed for applications within the healthcare sector. The recruited postdoctoral fellow will in particular be involved in projects where machine learning methods are applied to data from the Swedish register infrastructure to increase the quality and efficiency of healthcare. Focus will be on cardiometabolic diseases, such as early identification and prevention and improved diagnosis among patients seeking emergency care. The proposed solution is based on machine learning using electronic health records (EHR) (including electrocardiograms) and extensive health care registers. The project includes partners from both other faculties and healthcare providers.

Job assignments
The successful candidate will work with heterogeneous databases and pre-processing of medical data, and develop machine learning models, in part based on deep learning techniques, for diagnostic and predictive purposes. The project is truly cross-disciplinary and will be conducted in close collaboration with experts in areas such as emergency medicine, IT, epidemiology, statistics and language technology.

The employment will include opportunities for teaching and supervision corresponding to a maximum of 20% of full time. The position includes the opportunity for three weeks of training in higher education teaching and learning.

The principal duties will be:

• to undertake machine learning research and application development within different projects
• to contribute to academic publications and conference papers (and taking the lead on these when appropriate)
• to contribute to report writing

Qualification requirements
Appointment to a post-doctoral position requires that the applicant has a PhD, or an international degree deemed equivalent to a PhD, within the subject of the position, completed no more than three years before the last date for applications. Under special circumstances, the doctoral degree can have been completed earlier.

Assessment criteria
Postdoctoral fellow positions are research-focused appointments intended to form early stages of a science career. The assessment of the applicants will primarily be based on their research qualifications and potential as researchers. 

The applicant must hold a doctoral degree in machine learning, applied mathematics, computer science, or another relevant field such as epidemiology combined with sufficient knowledge and skills in applied machine learning methods. The applicant needs to demonstrate a strong research profile in the fields related to topics of interest for this position, including recent activities with high impact. The scientific production is expected to be published in high quality, peer-reviewed research journals and conference proceedings. The applicant should share the value that diversity and equality among researchers and teachers brings higher quality to research and education. 

Further mandatory requirements:

• good knowledge in spoken and written English
• solid experience in programming

Skills and experience regarded as advantageous:

• ability to conduct independent research
• experience in machine learning for medical applications
• experience in working with heterogeneous EHR data, including electrocardiograms
• good knowledge in spoken and written Swedish
• ability to attract external funding
• experience in supervision of master students

Terms of employment
This is a full-time, fixed-term employment of a maximum of 2 years. The period of employment is determined in accordance with the agreement “Avtal om tidsbegränsad anställning som postdoktor” (“Agreement on fixed-term employment as a post-doctoral fellow”) between Lund University, SACO-S, OFR/S and SEKO, dated 4 September 2008.

Application procedure
The application should include a CV, a personal letter, a publication list and a copy of the PhD degree diploma or documents supporting that a PhD degree will be obtained by the start of the employment, 

Contact
Machine learning: Professor Mattias Ohlsson, +46 46 2227782, mattias@thep.lu.se  
Emergency medicine: Ulf Ekelund, +46 46 176744, ulf.ekelund@med.lu.se
Epidemiology: Jonas Björk, +46 46 2226916, jonas.bjork@med.lu.se