AI Research Scientist -Computer Vision
Core
Enhance and manage the PlanGraph model to transform 2D construction drawings into structured graphical representations for downstream business use cases like quantity takeoff, code compliance, and constructability analysis.
Role type
Applied AI Research Scientist (Computer Vision)
Builds
Production-grade AI models (CV, VLMs, VLLMs) for construction intelligence workflows
Domain
Construction industry + Computer Vision / Multimodal AI
Deliverable
production ML models
Required skills
Computer Vision, Deep Learning, Machine Learning, Python, PyTorch, TensorFlow, OpenCV, image processing, object detection, segmentation, OCR, Vision Language Models (VLMs), Vision Transformers (ViTs), Generative AI concepts
Preferred skills
multi-step agent systems, applied AI research in startup/product environments, MLOps, model deployment, messy real-world data handling
Technologies
PyTorch, TensorFlow, OpenCV
Responsibilities
Build and optimize custom Computer Vision models, VLMs, and VLLMs; Solve downstream business use cases including quantity takeoff, code compliance, value engineering, and constructability analysis; Conduct applied research in Computer Vision, multimodal AI, document understanding, and spatial reasoning; Design, train, fine-tune, and evaluate production-grade AI models using large-scale datasets; Improve model accuracy, robustness, inference performance, and scalability for real-world deployment; Collaborate with engineering and product teams to convert research into deployable AI systems; Develop benchmarking, evaluation, and validation frameworks for model performance measurement; Contribute to research documentation, patents, publications, and internal technical knowledge sharing
Seniority
Mid-to-Senior, hands-on IC