SAU Data Scientist

The Compensation Range is the span between the minimum and maximum base salary for a position. The midpoint of the range is approximately halfway between the minimum and the maximum and represents an employee that possesses full job knowledge, qualifications and experience for the position. In the normal course, employees will be hired, transferred or promoted between the minimum and midpoint of the salary range for a job.

Note: Applications will be accepted until 11:59 PM on the Posting End Date.

Job End Date

At UBC, we believe that attracting and sustaining a diverse workforce is key to the successful pursuit of excellence in research, innovation, and learning for all faculty, staff and students. Our commitment to employment equity helps achieve inclusion and fairness, brings rich diversity to UBC as a workplace, and creates the necessary conditions for a rewarding career. 

Job Summary
The Sea Around Us is a research initiative, which, since its inception in 1994, has made available an online searchable Atlas of reconstructed marine capture fisheries catches from 1950 to the present of all maritime countries of the world via its website at www.seaaroundus.org. This global catch database permits the testing of fisheries-related global hypotheses applied to marine conservation concerns and has served as the underlying database for many articles published by the Sea Around Us members and their collaborators in peer-reviewed journals.

This position is responsible for the development of machine learning based tools for fisheries catch analysis, redesigning existing data-processing workflows, and building data visualization tools and interfaces for the Sea Around Us database and website.

This position supports the Sea Around Us in its continued effort to provide robust and reliable fisheries datasets for the public through modernizing the computational and analytical methodologies of the Sea Around Us system.
Organizational Status
The Data Scientist is a member of the core Sea Around Us team. This position reports directly to the Research Unit Manager, Dr Maria L.D. Palomares, and as required to the Principal Investigator, Dr. Daniel Pauly.
Work Performed
Statistical Modelling

• Consult closely with the Principal Investigator (PI) and Research Unit Manager to define research objectives, determine study design parameters, and select appropriate statistical methodologies.
• Evaluate and select statistical programs, R/Python packages, and machine-learning frameworks to ensure alignment with research objectives and study questions.
• Develop, implement, and maintain analytical models across multiple concurrent Sea Around Us research projects.
• Design and develop standardized protocols for incorporating underrepresented and small-scale fisheries data.
• Translate and interpret statistical results, enabling researchers and stakeholders to make informed, data-driven decisions.
• Compile, validate, and integrate new datasets (subsistence fisheries, gender-disaggregated data, Indigenous fisheries).
• Create validation workflows to test data integrity and document analytical methodologies to ensure transparency and reproducibility across the team.

Machine Learning Model Development

• Collaborate with subject expert and software engineering team to create scalable machine learning based models for fisheries analysis.
• Research and develop scalable end-to-end data science capabilities covering the full lifecycle of model creation. From data extraction and feature engineering to validation, deployment, and monitoring.
• Write, edit, and publish technical reports, working papers, and training materials based on a thorough understanding of subject matter, user needs, and industry best practices.
• Champion data integrity across the project. Educating other team members about best practices for analytical workflows, standardizing data preparation guidelines, and establishing data quality standards.

Project Coordination

• Establish realistic project timelines and sets clear milestones, ensuring all involved parties are aligned and aware of key dates.
• Regularly plan, execute, and report on projects with team and stakeholders, ensuring all tasks are on track and adjusting timelines as necessary.
• Maintain open lines of communication with all team members and stakeholders throughout the project lifecycle, ensuring clarity, addressing concerns, and fostering a collaborative environment.
• Prepare presentations, reports, documentation, and other deliverables as needed.

Consequence of Error/Judgement
This position requires the execution of a considerable amount of judgement, responsibility and initiative in determining work procedures, and methods. It also requires the coordination of work flows between the database team and domain experts. Incorrect decisions or judgment will directly affect the research group’s deliverable timelines, other research groups, NGOs and collaborators, and public users of our website and data. Errors in decision-making could negatively impact the reputation of the research lab, Program, Faculty and University.
Supervision Received
Routine work is carried out independently after completion of training, lab orientation, and familiarization with existing methods and projects. The role reports directly to the Research Unit Manager, Dr Maria Palomares and may defer to the Principal Investigator, Dr. Daniel Pauly for unusual occurrences. The successful candidate works independently under minimal supervision.
Supervision Given
The successful candidate provides technical direction and training to the Sea Around Us database and website teams, as well as student researchers on data analysis best practices and data literacy to broader staff. Additionally, the role acts as a specialized technical consultant to external research facilities, including local, national, and international collaborators on analytical and database challenges.
Minimum Qualifications
Post-graduate degree in Statistics. Minimum of two years of related experience in research analysis, or the equivalent combination of education and experience.

• Willingness to respect diverse perspectives, including perspectives in conflict with one’s own
• Demonstrates a commitment to enhancing one’s own awareness, knowledge, and skills related to equity, diversity, and inclusion

Preferred Qualifications

• Demonstrated experience working with large biological databases, specifically in fisheries.
• Proficient in Python, R, SQL, and MS Excel to work with large datasets (over 1 billion rows).
• Familiar with packages such as Pandas, scikit-learn, and PyTorch for data manipulation and building machine learning models.
• Knowledgeable in AWS cloud computing environments (S3, EC2, RDS).
• Experienced in the analysis and interpretation of fisheries-related data, identifying key information, determining implications, providing recommendations and effectively resolving issues.
• Ability to provide effective and appropriate guidance and counsel (e.g., providing data or instructions on how to obtain data through various methods to external researchers and advising on appropriate uses and interpretation of Sea Around Us data for their purposes).
• Experienced in writing clean, modular, and well-documented code following Data Science best practices.
• Effective oral and written communication and interpersonal skills.
• High level of initiative, curiosity, and willingness to experiment and innovate.
• Attention to detail and judgment in all work.
• Ability to give and receive feedback productively.
• Flexibility and ability to seek creative ideas to solve problems and identify new opportunities.
• Ability to prioritize and work effectively under pressure to meet deadlines and ensure multiple research projects within the research lab receive timely assistance.
• Ability to work effectively both independently and in close collaboration with a diverse range of partners and colleagues across campus.