Temporary Employment Opportunity at BC Cancer [CLOSED]

Temporary Employment Opportunity

Junior Data Scientist

BC Cancer Registry, Provincial Health Services Authority 

Vancouver, BC

Start Date: May 1^st , 2024

End Date: April 30^th, 2025 (extension possible)

The British Columbia Cancer Registry (BCCR) is a provincial population-based cancer registry, gold-certified by the North American Association of Central Cancer Registries. The BCCR captures population-based data on reportable tumors among British Columbians, providing comprehensive diagnosis and demographic details. The BCCR sits within Data, Analytics, Reporting, & Evaluation (DARE) at the Provincial Health Services Authority, which is a specialized portfolio that aims to deliver data and analytics solutions to help provide actionable insights, inform decisions, and improve outcomes and services for patients, populations, and staff. The BCCR’s mandate is to deliver timely, high-quality population-based data for cancer surveillance and research, facilitated by our multidisciplinary team employing advanced machine learning (ML). BCCR's portfolio involves:

• A dedicated team with expertise in cancer coding, business analysis, data integration, AI/ML, and epidemiology.
• Activities such as developing natural language processing pipelines for autocoding, cancer coding, auditing, and data consolidation from diverse sources (digital pathology reports, hospital discharge summaries, vital statistics, and hospital scheduling data).
• Active data submissions to NAACCR, Canadian Cancer Registry, and WHO/IARC, contributing to global cancer control/prevention efforts.

The BCCR is seeking a motivated data science professional to work with their cancer registry operations team in generating NLP pipelines on electronic pathology reports for information extraction and classification tasks. You will work with analytic team members and subject matter experts to co-design NLP solutions and generate code pipelines in Python to extract valuable information from a provincial feed of electronic cancer pathology reports to populate the cancer registry dataset. You will be involved in robust pipeline testing, implementation in production, and post-implementation monitoring. This is a temporary placement until April 30, 2025, with extension possibility. 

Qualifications/Skills: 

• MSc in Computer Science, Data Science, Statistics or a related discipline. Current students that otherwise meet qualifications who are able to commit to a reasonable number of weekly hours would be considered. 

• Deep fluency with and cultivation of modern coding practices in Python (functions, classes, packages such as pandas, numpy, pytorch, transformers, etc.)

• Experience with developing and working with the Shiny (R or Python) data visualization platform would be an asset

• Experience with key software development frameworks (version control, unit testing, modularization) an asset

• Experience with collaborative software development (GitHub) an asset

• Experience generating creative data visualizations that inform and engage broad audiences is an asset

• Able to work effectively with other analytic team members.

• Effective communication skills

• Careful attention to detail and validation of products. 

This position is able to work hybrid within BC and an office environment will be provided. 

UPDATE on APR 11, 2024: This job posting is now closed.