This position supports the application of mathematical modelling and computational modelling, e.g., machine learning, Bayesian statistics, and data analytics, for a broad range of problems of interest to CNL, including modelling and prediction of nuclear materials properties, prediction of component ageing and failure, modelling and prediction of radiological dispersion, image processing, and bioinformatics.
CNL seeks to leverage recent advances in applied mathematics and machine learning methods, in particular deep learning , to meet current and anticipated demand in the areas of contemporary and advanced fuel and structural materials modelling, nuclear security and safety response, and assessment of biological effects of radiation.
Exploitation of advanced computing methods for both traditional and emerging research areas in nuclear energy and safety will ensure that CNL is positioned to stay on the leading edge of nuclear research and development.
Successful candidates will be expected to develop methods and apply various mathematical models, algorithms and codes to relevant problems.
Specific areas include development of advanced algorithms to accelerate modelling of radiological dispersion, and use of machine learning to automate analysis and interpretation of microstructural imaging and associated materials performance data.
Additional areas of interest include the application of machine learning to image processing and microstructural analysis of nuclear fuel and structural components, statistical methods for component failure predictions, and the use of bioinformatics in characterization of the effects of radiation on biological systems.
Candidates will also be expected to participate in developing new techniques and methods that take advantage of advances in computing methods and hardware.
The candidate should be familiar with modern software tools, e.g. R, MATLAB, Python, and methods, e.g., Bayesian statistics, machine learning, and genomics.
The ability to perform parametric studies is also desirable.
It is expected that the candidate will have the ability to plan and execute complex scientific research tasks, focused on specific project objectives.
Presentations on research will be delivered internally to CNL, at national and international venues, and to external customers.
Work will be documented in internal CNL reports and published in peer reviewed journals.
New methods and technologies may be developed as an outcome of the research performed.
PhD in Engineering or Science from a university of recognized standing with a minimum of 2-5 years' experience, or membership in an engineering or scientific professional organization authorized by statute to establish qualification for membership in that organization.
Have 2-5 years of experience in an academic, industrial or institutional setting.
Strong communication skills and a proficiency in applied mathematics and computer programming are essential.
The candidate will be expected to both work in a team and perform independently.
The candidate is expected to report on progress through internal reports and presentations and to publish the results in peer reviewed journals.
Preference will be given to candidates with experience in applied mathematics, data analytics, machine learning, or Bayesian statistical models.
Knowledge and experience in bioinformatics and use of next generation sequencing analysis tools is also desirable.
CNL has an Employment Equity Program and encourages applications from women, Aboriginal Peoples, visible minorities and persons with disabilities