Matterport – Senior Machine Learning/Computer Vision Engineer – 3D Reconstruction and Semantic Understanding
Job Description
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 roleislocatedinour Sunnyvale, CAoffice and has a schedule of 4 days on-site and 1 dayremote.
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 6 including segmentation, depth estimation, multi-view geometry, and appearance modeling 6 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
- Master's or Ph.D. in Computer Vision, Machine Learning, Robotics, or a related field.
- 5+ years of industry experience developing and deploying computer vision or ML systems in production environments.
- Experience with camera pose estimation, visual odometry, SLAM, or structure-from-motion pipelines.
- Background in 3D reconstruction, NeRF, Gaussian Splatting, mesh processing, or related neural rendering methods.
- Experience applying semantic understanding, scene segmentation, or multi-modal learning to real-world capture or reconstruction pipelines.
- Familiarity with differentiable rendering, UV mapping, texture generation, or appearance modeling.
- Experience with performance optimization on GPUs (CUDA) or other hardware accelerators.
- Demonstrated ability to translate cutting-edge research into practical, robust, and scalable software solutions.
What9;s in it for you?
When you join CoStar Group, you9ll experience a collaborative and innovative culture working alongsidethe best and brightest to empower our people and customers to succeed. We offer you generous compensation and performance-based incentives. CoStar Group also invests inyour professional and academic growth with internal training and tuition reimbursement.
Our benefits package includes (but is not limited to):
- Comprehensive healthcare coverage: Medical / Vision / Dental / Prescription Drug
- Life, legal, and supplementary insurance
- Virtual and in person mental health counseling services for individuals and family
- Commuter and parking benefits
- 401(K) retirement plan with matching contributions
- Employee stock purchase plan
- Paid time off
- Tuition reimbursement
- On-site fitness center and/or reimbursed fitness center membership costs (location dependent)
- Access to CoStar Group9s Employee Resource Groups
- Complimentary gourmet coffee, tea, hot chocolate, fresh fruit, and other healthy snack
This position offersa base salary range from $190,000 to $253,000 a year,determinedby relevant skills and experience, and a generous benefits plan.
#Matterport #LI-VP1