Job Overview
This role involves building AI-driven capabilities for a property technology platform, focusing on computer vision and document understanding to analyze visual and document-based data for automated decision-making. You will collaborate with product and engineering teams to design, build, and deploy reliable machine learning solutions in production.
Responsibilities
- Design, develop, and deploy computer vision and machine learning models for analyzing visual and document-based data.
- Build pipelines that convert unstructured visual inputs into structured and usable information.
- Develop and evaluate models for tasks such as object detection, segmentation, document parsing, and image understanding.
- Apply OCR and related techniques to extract meaningful information from complex documents and imagery.
- Work with large datasets and build efficient training and evaluation pipelines.
- Handle real-world visual datasets that may contain noise, inconsistencies, incomplete information, or varying formats.
- Experiment with different approaches to solve challenging computer vision problems and evaluate tradeoffs between accuracy, performance, and complexity.
- Collaborate with product and engineering teams to integrate machine learning models into scalable production systems.
- Continuously improve model performance, accuracy, and robustness in real-world environments.
- Stay up to date with the latest developments in AI and computer vision and apply relevant techniques where appropriate.
- Actively leverage modern AI tools and frameworks to accelerate experimentation, development, and engineering workflows.
Qualifications
- 5+ years of hands-on experience building and deploying machine learning models, particularly in Computer Vision or document understanding.
- Strong proficiency in Python for machine learning and data processing.
- Hands-on experience with modern ML frameworks such as PyTorch and libraries in the Hugging Face ecosystem.
- Experience with computer vision tooling such as OpenCV.
- Experience with common ML and data science libraries such as scikit-learn, NumPy, and Pandas.
- Experience developing models for tasks such as segmentation, object detection, or document analysis.
- Experience working with large image datasets and building training pipelines.
- Solid understanding of model evaluation, data preprocessing, and performance optimization.
- Strong problem-solving skills and ability to work in a fast-paced product environment.
- Ability to collaborate effectively with cross-functional engineering and product teams.
Preferred Qualifications
- Experience with TensorFlow or other deep learning frameworks.
- Experience working with OCR pipelines or document analysis systems.
- Experience deploying machine learning models in production environments.
- Experience with containerized deployments such as Docker or Kubernetes.
- Experience working with complex technical documents, diagrams, or structured visual data.
- Familiarity with spatial or geometry-related data problems.
