Edge Machine Learning Engineer Toronto

Optimize machine learning for resource-constrained edge devices at Invision AI, combining Python, computer vision, and production systems expertise. Work hybrid from downtown Toronto three days weekly.This full-time Machine Learning Engineer position focuses on building and maintaining models used in real-world products. You will improve object detection, image classification, geospatial tracking, and sensor fusion capabilities. The work spans training pipelines, deployment, monitoring, model drift, data quality, and ongoing retraining needs.Key Responsibilities:
Optimize model latency, memory usage, power consumption, and accuracyRecommend and deploy models across product linesIdentify model drift, data problems, and retraining requirementsPrototype capabilities with appropriate technologiesResolve issues affecting deployed machine learning modelsRequirements:
Hands-on optimization experience in edge environmentsWorking knowledge of embedded systems and constraintsStrong Python development and software engineering practicesKnowledge of experiment tracking, dataset versioning, and observabilityUnderstanding of production monitoring and troubleshootingBring edge optimization, embedded systems, and computer vision experience to Invision AI’s Toronto engineering team.
#J-18808-Ljbffr