TRIUMF Canada's National Laboratory for Particle and Nuclear Physics STUDENT JOB PROGRAM Summer 2020 job posting Job number TR20-2-6 | ||
---|---|---|
Position Title:Junior machine learning engineer | ||
Name of Project:AI-supported accelerator tuning | ||
Overview:TRIUMF accelerator complex enables world class research in fields ranging from nuclear physics to material sciences, life sciences and nuclear medicine offering a major advantage in probing nuclear physics processes and uniquely place TRIUMF as a leader in experiments at the “precision frontier” to address some of the fundamental scientific questions of our time. The priorities of the accelerator physics research at TRIUMF include the support for operation and development of TRIUMF accelerators, target systems and beam lines.To deliver isotope beam produced by the ISAC facility and ARIEL in the future with the desired intensity and quality to various nuclear physics experiments, multiple parameters of the ISAC-I accelerator need to be tuned during a lengthy, manual procedure. Tuning process must be performed after any adjustments or maintenance of the accelerator. The student will develop a framework for the automated procedure of control of the accelerator utilizing modern machine learning techniques such as reinforcement learning. Modern model-free and model-based techniques will be explored. Input from accelerator physicists in designing the desired qualities of the control mechanisms will be incorporated into the machine learning models. The student will utilize and configure existing accelerator simulation packages and develop a software environment for interfacing the machine learning methods to the simulation environments as well as the actual accelerator controls. | ||
Duties:Duties of the student will include- Development of machine learning techniques for accelerator control. - Utilizing existing software packages to build simulation environments for beamlines. - Development of software framework for interfacing the model to machine controls. - Development of software framework for interfacing the model to simulation environments. - Model training and performance evaluation. - Collaboration with beam physicists and machine operators. - Presentations and reports to peers and experts in the field. | ||
Skills learned during this work experience:- Ability to tackle a complex, multi-faceted problem- Deep learning - Reinforcement learning - Experience with deep learning libraries (pytorch) and artificial intelligence environments (Open-AI gym) - Accelerator physics - Oral and written presentation skills | ||
Qualifications:The position targets a senior undergraduate in an Engineering-Physics, joint Physics and Computer Science, Computer and Electrical Engineering or similar programme.Ideally the candidate will have completed at least one work term. Qualifications required: - Strong knowledge of physics curriculum at senior undergraduate level. - Strong background in python programming. - Experience with numerical libraries in python: numpy, matplotlib, scikit-learn - Basic knowledge of statistics and machine learning concepts. Beneficial experience: - Concepts in accelerator physics - Concepts in deep learning and reinforcement learning. - Concepts in control theory (e.g. PID) - Experience with deep learning libraries in python (pytorch, tensorflow) - C++ programming experience - Experience with batch processing systems (slurm, torque) - Experience with versioning tools (git) | ||
Shiftwork required:No | ||
Period of work:May - Aug 2020 with possible 4-month extension | ||
Salary is commensurate with academic progress and previous relevant work experience, and
ranges from $ 2080 to $ 2800 per month plus 4% vacation pay. TRIUMF pays round-trip airfare (this does not apply to Vancouver/Victoria students); for Vancouver Island students, TRIUMF will pay ferry costs.
TRIUMF is an equal opportunity employer committed to diversity in the workplace, and we
welcome applications from all qualified undergraduate students as defined below:
Applications must be received at TRIUMF by 4:00pm Pacific time on 2020-01-26. To apply for any of the job postings, you must submit one application for each and every job for which you wish to be considered. Please combine all documents into one PDF for each job. All applications can be attached to one email in PDF format. Please do not send electronic documents in formats other than PDF. Please save the PDF as lastname-job number (eg Smith-15.pdf)
Students within an university co-op program MUST apply for TRIUMF jobs through their university co-op education office.
No phone calls please. TRIUMF wishes to thank all applicants for their interest, and regrets that only those being considered will be contacted.
For more information, visit our web site http://www.triumf.ca |