Machine Learning Engineer (Remote/Toronto)

Job summary

This role involves taking ownership of the entire lifecycle of machine learning systems that support an indoor mapping platform, focusing on computer vision and geospatial data. The position requires hands-on work to optimize model performance for real-world applications in complex indoor environments.

Qualifications

• 3–5+ years of experience in building production machine learning systems
• Strong proficiency in Python with a focus on clean and maintainable code
• Experience with deep learning frameworks, preferably PyTorch
• Solid background in computer vision techniques such as object detection and segmentation
• Understanding of machine learning systems, training pipelines, and model versioning
• Familiarity with cloud platforms like GCP, AWS, or Azure
• Knowledge of containers and orchestration for production deployment
• Strong grasp of model evaluation and performance metrics

Responsibilities

• Manage the full lifecycle of machine learning systems from data ingestion to deployment and monitoring
• Address challenges in generalizing models across diverse architectural inputs
• Transform raw predictions into usable spatial data
• Optimize inference processes at scale
• Shape the direction of the machine learning pipeline and explore innovative approaches

Skills

• Experience with geospatial data and spatial databases
• Familiarity with architectural drawings and structured building data
• Exposure to foundation models or vision-language models
• Experience in optimizing models for inference and hardware acceleration
• Background in related fields such as robotics or medical imaging
• Engagement with the machine learning community through contributions or research

Education

• Degree in Computer Science, Machine Learning, Mathematics, Physics, Engineering, or related field preferred, but alternative educational paths are also considered.

Tools

• Python, PyTorch, cloud platforms (GCP, AWS, Azure), containers, orchestration tools.