ML Research

Description

Develop and optimize computer vision, machine learning and NLP models for construction document analysis Research and implement state-of-the-art techniques for construction document analysis and error detection Contribute to the evaluation and integration of emerging AI technologies (foundation models, multimodal AI, agentic processing) into our platform Build and maintain OCR and document understanding systems optimized for engineering drawings Participate in data strategy activities including collection, annotation pipeline development, and curation of construction document datasets Collaborate with the team on domain and product requirements, model evaluation, iteration, and production deployment

Requirements

• At least 3 years of industry experience in machine learning, NLP, computer vision, or a related field
• Proficiency with deep learning frameworks (PyTorch, TensorFlow) and MLOps practices
• Strong software engineering fundamentals (version control, testing, code review)
• BSc in Computer Science, Machine Learning, Computer Vision, or related field

Preferred Qualifications

• MSc in a relevant field
• Familiarity with transformer architectures, foundation models, and agentic AI pipelines
• Hands-on experience deploying ML models in production environments
• Exposure to multi-stakeholder AI projects from research through to production deployment
• Familiarity with construction documents