POSITION TITLE |
Post-Doctoral Fellowship |
DEPARTMENT |
LTRI |
EMPLOYMENT TYPE |
Full-time |
HOURS OF WORK |
37.5 hours per week |
EMPLOYEE GROUP |
Non-Union |
REPORTS TO |
Principal Investigator |
ORGANIZATION
The Lunenfeld-Tanenbaum Research Institute of Mount Sinai Hospital, a University of Toronto affiliated research centre, is one of the world's leading centres in biomedical research. With ground-breaking discoveries in research areas such as diabetes, genetic disorders, cancer and women’s and infants’ health, the Institute is committed to excellence in health research and the training of young investigators. Strong partnerships with the clinical programs of Mount Sinai Hospital ensure that scientific knowledge is used to promote human health. Your significant contributions will assist in maintaining our momentum in advancing our research.
The Campbell (https://www.camlab.ca) and Durocher (https://durocherlab.org/) labs are searching for a postdoctoral fellow to develop and apply machine learning methods to map synthetic lethal dependencies in cancer. Based at the Lunenfeld-Tanenbaum Research Institute of Sinai Health System and the Departments of Molecular Genetics and Statistical Sciences, University of Toronto, we are a highly collaborative group working on applications of machine learning across multiple aspects of cancer genomics.
POSITION OVERVIEW
We have an opening for a postdoctoral fellow to lead an exciting collaborative machine learning project to identify synthetic lethal interactions in cancer cells. They will develop a set of sophisticated deep learning models for genetic dependency prediction that will be tested in the lab with the resulting data fed back in to improve modelling, creating the most diverse synthetic lethal interaction atlas to-date. The fellow will have a unique opportunity to collaborate in a multi-disciplinary environment, developing computational models that lead to immediately testable predictions the lab.
This position has scope for significant freedom of research direction in computational methods development, following our lab’s strong track record in this area. The applicant will be supported to attend national and international conferences to present work and network, and publish results in top journals. The applicant can also supervise junior researchers within the group to build a strong mentorship portfolio for future academic or industry roles. This position will be supported by a competitive salary, access to state-of-the-art compute infrastructure as well as the thriving machine learning community in Toronto’s discovery district.
For informal enquiries about the position, please email kierancampbell@lunenfeld.ca
To apply please use URL http://apply.interfolio.com/162929
DUTIES AND RESPONSIBILITIES
- Develop state-of-the-art active machine learning methods for genetic dependency prediction
- Engineer strong multi-modal feature sets for prediction and target search
- Communicate candidate targets to collaborators and iterate model development incorporating new data
- Write and publish research papers in journals
- Attend and present work at international conferences
- Mentor junior researchers in the group
SKILLS/QUALIFICATIONS
Essential Skills
- A strong computational background with a bachelors/masters/PhD in computational biology, machine learning, statistics, or related fields
- Evidence of advanced computer programming capability using Python and/or R within a research setting.
- Evidence of proficiency in supervised machine learning, including understanding model complexity, train/test splits, and hyperparameter optimization
- An appreciation or enthusiasm for cancer biology and computational methods development
- Demonstrate strong interpersonal skills through experience of working within a scientific research team or collaboration.
Desired Skills
- A track record of publications in machine learning and computational biology
- Proficiency with Pytorch and Pytorch-geometric deep learning frameworks along with ML performance monitoring (e.g. weights and biases, or similar)
- Experience applying active learning to biological datasets and retraining models incorporating new data
- Proficiency analyzing CRISPR knockout screens
- Experience managing collaborative projects and mentoring junior researchers
Application Instructions
Apply online through Interfolio http://apply.interfolio.com/162929
1) A cover letter, referencing your suitability for the role, enthusiasm for the research area, and availability
2) An academic CV including education, publications, and links to previously created open source software / machine learning projects
3) Contact details for two referees, including name and email
In accordance with Institute’s policy and legislated health and safety requirements, employment is conditional upon the verification of credentials, completion of a health review, and demonstrating proof of immunity and vaccination status of vaccine-preventable diseases. Successful candidates will be required to provide two (2) written reference letters from their former employer(s)/supervisor(s).
We are a fully committed to fairness and equity in employment and our recruitment and selection practices. We encourage applications from Indigenous peoples, people with disabilities, members of sexual minority groups, members of racialized groups, women and any others who may contribute to the further diversification of our Sinai Health community. Accommodation will be provided in all parts of the hiring process as required under our Access for People with Disabilities policy. Applicants need to make their requirements known in advance.
The Lunenfeld-Tanenbaum Research Institute is a scent sensitive environment and all members of the community are expected to refrain from wearing or using scented products while visiting or working at the Institute. We also support a barrier-free workplace supported by the Institute’s accessibility plan, accommodation and disability management policies and procedures. Should you require accommodation at any point during the recruitment process, including accessible job postings, please contact the Lunenfeld-Tanenbaum Human Resources Department.
Posting open until March 9, 2025. We thank all candidates for applying. Only those selected for an interview will be contacted. |
|