AI Engineer [Computer Vision]
Core
Design, develop, and productionize advanced computer vision systems to interpret visual data (images, drawings, site photos) and connect them with verified technical knowledge, taxonomy, and knowledge graphs for the construction industry.
Role type
Senior Computer Vision Engineer (Construction Domain)
Builds
Scalable perception systems for object detection, segmentation, OCR, visual matching, and multimodal vision-language applications.
Domain
Construction industry, Knowledge Graphs, Linked Data, Computer Vision
Deliverable
production ML models
Required skills
Deep learning frameworks, Object detection, Image segmentation, OCR, Visual matching, Model optimization, GPU/CPU inference, Data preprocessing, Automated testing workflows
Preferred skills
Multimodal vision-language applications, Video analytics, Dataset design and annotation
Technologies
Deep learning frameworks, GPU, CPU
Responsibilities
Design and evaluate robust computer vision models and pipelines; Build end-to-end vision systems from data preprocessing to deployment; Develop systems for object detection, segmentation, tracking, and OCR; Collaborate to connect visual AI outputs with ontology and knowledge graph layers; Optimize models for scalability and latency; Contribute to dataset design and data quality validation.
