Machine Learning Applied Scientist (Co-op)

Location: In-person at the Vancouver, British Columbia office, Canada. The co-op term runs from January 2027 through August 2027.

Salary: CAD $3,600–$4,500 per month

Company

hirify.global develops 4D vision software, simulation tools, and robotic bin-picking solutions for automotive and industrial manufacturing.

What you will do

• Prototype and evaluate machine learning models for object detection, depth estimation, and 6-DoF pose estimation.
• Benchmark models on internal datasets representing real manufacturing conditions.
• Adapt recent machine learning and computer vision research to improve model speed, stability, and accuracy.
• Improve synthetic data generation by expanding variation in object shape, material, and pose.
• Collaborate with robotics and software engineers to diagnose and resolve model issues in simulation and robotic testing.
• Own a scoped machine learning project and present outcomes with metrics and insights at the end of the term.

Requirements

• Proficiency in Python and machine learning frameworks such as PyTorch.
• Understanding of computer vision fundamentals, including detection, segmentation, and 3D geometry.
• Familiarity with model training, tuning, and evaluation workflows.
• Interest in robotics or applying machine learning in production-grade software.
• Ability to work in person at the Vancouver office for the 8-month co-op term.

Nice to have

• Experience with synthetic data generation or Blender.
• Exposure to 6-DoF pose estimation, point cloud processing, or depth sensing.
• Experience with Linux or Docker-based environments.
• Familiarity with AWS services such as S3, EC2, or SageMaker.

Culture & Benefits

• Hands-on experience applying academic machine learning concepts to production workflows.
• Opportunity to work with internal datasets and models deployed on industrial robots.
• Collaborative, fast-moving, and impact-driven environment.
• Exposure to simulation and real customer-facing robotic solutions.
• Work focused on practical machine learning challenges in industrial automation.