Staff Machine Learning & Computer Vision Engineer
DandyFull Time
Senior (5 to 8 years)
Candidates should possess a Master’s or Doctoral degree in Computer Science, Computer Vision, Robotics, or a related field, with a minimum of 5 years of experience in computer vision, specifically focused on building production-ready systems. Proficiency in Python, experience with deep learning frameworks such as PyTorch or TensorFlow, and familiarity with computer vision libraries like OpenCV are required. Strong experience in image processing, feature extraction, and visual data analysis is also necessary. Familiarity with visual transformers and their applications in computer vision tasks is expected.
The Computer Vision Engineer will enhance the company’s capabilities to understand and extract information from images in the construction domain, including blueprints, schematics, and site photos. They will develop and deploy computer vision models such as image classification, object detection, and segmentation, building and optimizing pipelines for integrating vision models into existing workflows. The role also involves designing efficient labeling processes to acquire proprietary datasets for training algorithms, processing and analyzing a diverse set of documents beyond images, including text and tables, and conducting experiments to evaluate and improve model performance and robustness.
AI-driven incentive management software for construction
Trunk Tools offers incentive management software tailored for the construction industry, featuring products like TrunkText and TrunkPerform. TrunkText uses artificial intelligence to help users quickly find project documents, while TrunkPerform enhances project performance by speeding up task completion. The company operates on a subscription-based model, providing software-as-a-service (SaaS) solutions that generate steady revenue. Trunk Tools aims to improve efficiency and productivity for construction professionals, distinguishing itself from competitors by focusing on their specific needs.