Senior Computer Vision Engineer- Canada
$250,000–$280,000 year
RemoteUnited States
Job Summary
Design end-to-end detection and segmentation pipelines for construction document images, improving ingestion for PDFs and unstructured files through parsing, rendering, and multi-page handling. Increase model accuracy, boundary quality, and geometric precision while integrating modern architectures into production workflows with robust post-processing. Define evaluation metrics, investigate failure cases, and optimize latency, reliability, and cost across the inference stack. Own training infrastructure, dataset curation, and continuous-improvement loops to ensure systems perform consistently under real-world constraints.
Required Qualifications
- Experience building computer vision systems: detection, segmentation, or structured geometry extraction, used high volume in production
- Experience working with messy, real-world image data or large unstructured visual datasets
- Strong understanding of detection and segmentation tradeoffs, including model architecture choices, training data design, and post-processing
- Ability to measure system performance with evaluation, testing, and production metrics
- Ability to explain failure modes clearly and improve systems through debugging, dataset work, and iteration
- Experience with multimodal models (vision-language models, document AI systems)
- Understanding of grounding — linking model outputs to source data or coordinates
- Backend engineering experience, including APIs, async processing, and scalable GPU services
Desired Qualifications
- Experience with polygon or mask post-processing, geometric regularization, or CAD-style structured output
- Experience with layout-aware document processing, PDF vector extraction, or combining raster and vector signals
- Background in document-heavy CV domains such as construction, real estate, medical imaging, geospatial, or similar workflows
- Experience optimizing inference cost and latency at scale
- Familiarity with open-source detection / segmentation ecosystems, training infrastructure, or model serving
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.