Matterport - Senior Machine Learning/Computer Vision Engineer - 3D Reconstruction and Semantic Understanding
Matterport - Senior Machine Learning/Computer Vision Engineer - 3D Reconstruction and Semantic Understanding Job Description
Company Overview:
CoStar Group (NASDAQ: CSGP) is a leading global provider of commercial and residential real estate information, analytics, and online marketplaces. Included in the S&P 500 Index, CoStar Group is on a mission to digitize the world's real estate, empowering all people to discover properties, insights and connections that improve their businesses and lives. We have been living and breathing the world of real estate information and online marketplaces for over 35 years, giving us the perspective to create truly unique and valuable offerings to our customers. We've continually refined, transformed, and perfected our approach to our business, creating a language that has become standard in our industry, for our customers, and even our competitors. We continue that effort today and are always working to improve and drive innovation. This is how we deliver for our customers, our employees, and investors. By equipping the brightest minds with the best resources available, we provide an invaluable edge in real estate.
About Matterport
Matterport is leading the digital transformation of the built world. Our groundbreaking spatial computing platform turns buildings into data, making every space more valuable and accessible. Millions of buildings in more than 170 countries have been transformed into immersive Matterport digital twins to improve every part of the building lifecycle - from planning, construction, and operations to documentation, appraisal, and marketing.
About the Role
As a Senior Machine Learning/Computer Vision Engineer on our Vision & Learning team, you will drive the research, design, and production deployment of state-of-the-art machine learning and computer vision systems at the core of our spatial capture and reconstruction platform. You will be a key contributor across the full vision pipeline - from intelligent capture guidance to 3D reconstruction and asset delivery - ensuring the highest possible quality of the digital twins our users create. You will work at the intersection of applied research and engineering, tackling hard problems in camera pose estimation, 3D scene reconstruction, semantic understanding, and visual perception. Your work will directly shape both the capture experience we provide to users and the quality of the assets we deliver to customers. This role is located in our Sunnyvale, CA office and has a schedule of 4 days on-site and 1 day remote.
What You Will Do
+ Research, develop, and improve camera pose estimation algorithms to enable accurate, robust localization and spatial understanding across diverse capture scenarios. + Advance mesh generation, surface reconstruction, and texturing pipelines to produce high-fidelity, production-ready 3D assets at scale. + Design and implement intelligent systems that leverage semantic scene understanding to guide and optimize the capture process in real time, improving both user experience and output quality. + Apply deep learning and foundation model techniques across the vision pipeline - including segmentation, depth estimation, multi-view geometry, and appearance modeling - to improve robustness and generalization. + Collaborate with hardware, software, and product teams to identify and address failure modes across the end-to-end pipeline through data-driven analysis and targeted model improvements. + Contribute to the full ML lifecycle: data collection strategy, model training, evaluation frameworks, production deployment, and ongoing monitoring. + Research and prototype novel computer vision and machine learning techniques to advance the quality, speed, and robustness of our 3D reconstruction and capture systems. + Stay current with the latest advances in computer vision, neural rendering, and 3D ML; evaluate and integrate relevant research into production systems. + Write high-quality, well-tested, and maintainable Python and C++ code.
Basic Qualifications
+ Bachelor's degree in Computer Science, Electrical Engineering, Mathematics, or a related quantitative field, or equivalent practical experience from an accredited, not-for-profit, in-person University or College + A proven track record of commitment to prior employers. + 3+ years of hands-on experience in machine learning and computer vision. + Strong programming skills in Python and C++. + Deep understanding of computer vision fundamentals including 3D geometry, multi-view reconstruction, and image formation. + Experience with deep learning frameworks (e.g., PyTorch, JAX) and computer vision libraries (e.g., OpenCV). + Experience with version control systems (e.g., Git) and agile development methodologies. + Excellent problem-solving skills and a strong ability to debug complex, multi-component systems. + Strong verbal and written communication skills.
Preferred Qualifications
+ Mast