Senior Computer Vision Engineer, OpenSpace
Machine Learning
$152-239.5k
+ Equity
3D mapping software for construction
Open for applications
3D mapping software for construction
201-500 employees
Open for applications
$152-239.5k
+ Equity
201-500 employees
Company mission
To bring new levels of transparency to construction.
Role
Who you are
- M.S./Ph.D. in related field or equivalent industry experience
- 5+ years of industry experience developing computer vision and machine learning models for image processing
- Strong expertise in camera models, camera calibration, and 3D pose representations and transforms
- Experience with at least one of the following: SLAM, SfM, 3D reconstruction, photogrammetry, or Visual Inertial Odometry (VIO)
- Experience working with IMU and other sensor data
- Deep understanding of fundamental CV techniques: feature detection and matching, probabilistic modeling, computational geometry, numerical optimization
- Proficiency in deep learning frameworks such as PyTorch or TensorFlow
- Expertise in Python programming and numerical algorithm implementation
- Experience working with multi-modal models combining images and language
- Familiarity with 3D visualizations and debug interfaces (OpenGL/PyQt)
- Proficiency in cloud computing platforms (AWS, GCP, or equivalent) and software version control systems (Git)
- Strong problem-solving skills and the ability to work on interdisciplinary challenges at the intersection of computer vision, deep learning, and 3D perception
- Excellent written and verbal communication skills, with the ability to convey complex technical concepts clearly
What the job involves
- We're looking for an experienced AI engineer to work on improving the core pieces of our mapping and localization capabilities. The focus of the Senior Computer Vision & Machine Learning Engineer is to enhance our mapping, localization, and 3D reconstruction capabilities
- This role focuses primarily on computer vision techniques but also integrates machine learning methodologies to optimize performance on real-world construction site data
- You will be working with the AI team to develop innovative solutions leveraging classical computer vision, probabilistic modeling, computational geometry, and deep learning to provide meaningful insights to our customers
- Design and architect complex, multi-component computer vision and machine learning systems
- Develop and optimize image localization, SLAM, Structure from Motion (SfM), and 3D reconstruction techniques
- Implement deep learning models for visual perception, leveraging modern machine learning techniques (LLMs, VLLMs, transformers, multi-modal models, and generative AI)
- Prototype and rigorously test algorithms on real-world construction site data
- Collaborate with platform engineers to transition research prototypes into production-ready implementations
- Oversee dataset creation, curation, and annotation to ensure high-quality training and validation data
- Monitor and improve system performance in production, ensuring robustness and scalability
- Debug and resolve complex failure edge cases in the production processing pipeline
- Contribute to defining development processes, best practices, and documentation
Our take
360 photos and virtual tours are nothing new. Popularly used to enhance estate agent listings, or create tours of attractions, tools such as Kuula, Panoskin, and Matterport have captured that market. But OpenSpace is applying similar technologies to another industry sector - construction.
With a simple store-bought camera attached to a hard hat, a site walk-through creates a virtual 3D replica of any space. This detailed capture, reminiscent of Google Street View, eliminates the need for site visits, saving time and also reducing risks of visitors to building sites.
Other 360 virtual tour companies will probably offer their services to construction in the future, but OpenSpace hopes to keep the lead with its superior processing speed. (Its approach creates results in just fifteen minutes as opposed to the hours or days of other systems.) It is also well-funded, so can get on with scaling the business and developing additional AI-powered technologies to keep its value up.
Kirsty
Company Specialist at Welcome to the Jungle
Insights
14% employee growth in 12 months
Company
Funding (last 2 of 7 rounds)
Aug 2022
$9m
SERIES D
Mar 2022
$102m
SERIES D
Total funding: $200.1m
Company benefits
- Generous time-off
- Ample parental leave
- Healthcare
- Retirement savings program
Company HQ
Chinatown, San Francisco, CA
Leadership
Jeevan Kalanithi
(CEO & Co-Founder)Sold their first company, Sifteo, to 3D Robotics, where they became the President. Was also VP Product, CPO and President at 3DR.
Philip DeCamp
(Chief Engineer & Co-Founder)Former computer vision and data visualization research scientist at MIT, where they completed their PhD.
Michael Fleischman
(CTO & Co-Founder)After completing their PhD at MIT, they started Bluefin Labs, a company that specialized in the analysis of massive amounts of video. Twitter acquired Bluefin in one of its largest acquisitions.
Share this job
View 3 more jobs at OpenSpace