Software Engineer, Crop Computer Vision and Machine Learning

Canada’s crop production is being increasingly challenged by climate change, more prevalent weather extremes, and emerging disease threats. Designing transformative computer vision and machine learning systems to boost efficiencies and design resilient crops is critical to our agriculture industry. Automated vision analysis of crop roots and the rhizosphere presents a unique opportunity to increase the genetic gains and adaptability of Canada’s field crops. At the NRC’s Aquatic and Crop Resource Development (ACRD) research centre, we are investing in technologies to image and analyze crop root and shoot systems, increasing the use of machine learning and generative AI solutions, and expanding our digital capabilities to develop innovative tools for crop improvement and agricultural productivity. We invite you to join our team to take crop phenomics to the next level and be an integral member contributing to making Canada’s crops more resilient. Interacting with colleagues across ACRD and collaborating nationally and internationally, the successful candidate would be someone who shares our core values of Integrity, Excellence, Respect and Creativity.

As a Computer Vision specialist on the Integrated Omics and Climate Resilience Team at ACRD, you will play a key role in helping position the NRC as leaders in digital research for Canada. Your responsibilities include the delivery of software support for the design, development, and implementation of computer code which enables automated analyses of crop images. This would include supporting ACRD efforts for implementing best practices and new tools for data management. The successful candidate is also expected to mentor and lead Computer Systems administrators, Technical Officers, and Research Officers colleagues and students for accomplishment of projects focused on Computer Vision and Machine Learning.

Applicants must demonstrate within the content of their application that they meet the following screening criteria in order to be given further consideration as candidates:

M.Sc. in Computer Science, Electrical Engineering, or a related field. Candidates with a B.Sc. and at least 2 years of relevant experience in developing computer vision or machine learning algorithms will also be considered.

For information on certificates and diplomas issued abroad, please see Degree equivalency

Significant experience* in computer vision approaches with proven track-record of developing algorithms, documentation, and production-quality software code for image analysis. Experience*** with biological or agricultural images is an asset.

Strong proficiency** in Python and experience*** with C++ for performance‑critical computer vision applications.

Experience*** in computational geometry, 3D representations and related data structures.

Experience*** developing and training deep learning models for computer vision, including convolutional neural networks (CNNs), vision transformers, and foundation models.

Experience*** mentoring junior developers, engineers, or students in machine learning or computer vision methods and software development best practices.

Experience*** in parallel processing (e.g., across GPUs) and multi-threaded application design is preferred.

Experience*** with transfer learning techniques to leverage pre-trained models, including large foundation models, will be considered an asset .

* Significant experience is defined as 3+ years of directly relevant experience, with demonstrated application across multiple projects. ** Strong proficiency is defined as 3+ years of experience, with demonstrated ability to independently develop, debug, and maintain code across multiple projects. *** Experience is defined as 2+ years of hands-on experience, with demonstrated application in one or more projects.

Reliability Status

For a Reliability Status, verification of background information over a period of 5 years is required.

Candidates will be assessed on the basis of the following criteria:

Knowledge of classical computer-vision methods including pre-processing, segmentation, object detection and classification including foundational theory and familiarity with OpenCV or similar frameworks.

Knowledge of 3D reconstruction techniques and generation of 3D representations such as point clouds or meshes.

Understanding of deep learning methods for computer vision and their application to image analysis.

Proficiency in training dataset preparation, including preprocessing, augmentation, and annotation, and familiarity with self-supervised or representation learning approaches.

Proficiency in modern deep learning frameworks such as PyTorch or TensorFlow.

Familiarity with model evaluation, validation, and performance metrics for computer vision tasks.

Ability to use version control systems (e.g., Git) and workflow or pipeline tools to support reproducible machine learning experiments and data processing (e.g., Snakemake, MLflow, or similar).

Practical knowledge of open-source frameworks for federated learning will be considered an asset .

Technology support - Communication (Level 2)

Technology support - Conceptual and analytical ability (Level 3)

Technology support - Initiative (Level 2)

Technology support - Self-knowing and self-development (Level 3)

Technology support - Teamwork (Level 2)

For this position, the NRC will evaluate candidates using the following competency profile(s): Technology Support

View all competency profiles

In 2025, the NRC was chosen as one of Canada’s Top Employers for Young People, a National Capital Region Top Employer and Forbes Canada’s Best Employer.

Relocation assistance will be determined in accordance with the NRC's directives.

A pre-qualified list may be established for similar positions for a one year period.

Preference will be given to Canadian Citizens and Permanent Residents of Canada. Please include citizenship information in your application.

The incumbent must adhere to safe workplace practices at all times.

We thank all those who apply, however only those selected for further consideration will be contacted.

Please direct your questions, with the requisition number (25241) to:

E-mail: NRC.NRCHiring-EmbaucheCNRC.CNRC@nrc-cnrc.gc.ca

Telephone: 3439909603

Closing Date: 22 September 2026 - 23:59 Eastern Time

For more information on career tools and other resources, check out Career tools and resources

*If you are currently a term or continuing employee at NRC, please apply through the SuccessFactors Careers module from your NRC computer.