Ascent is working on multiple projects involving advanced computer vision, leveraging classic approaches as well as Machine Learning techniques. As a Computer Vision Engineer you will work on state of the art algorithms, while building the ideal software environment and infrastructure to support Ascent solutions.
The work we do presents interesting and unique engineering challenges. You will work on some of different areas such as sensor calibration, photogrammetry, image classification, object pose detection, inverse rendering, etc. You will have the possibility to be involved and have an impact on full solutions.
As a member of the Engineering Team, you’ll be part of a highly collaborative team who can work closely together and help each other on different tasks. This will involve developing, testing and enhancing software solutions based on requirements from a multitude of stakeholders including researchers, team leads and program managers.
- You will be working with the Engineering team to develop and improve Ascent 3D Scanning solution
- Understand, reproduce and adapt state of the art techniques to real world use cases
- Architect and implement software libraries and internal tools
- Write and maintain documentation for the code you write
- Integrate our software, build APIs and databases
- Try new technologies that may make things better. We are not constrained by legacy code
- Bachelor’s degree in Computer Science, Computer Engineering or a related technical field, or equivalent experience.
- Strong software engineer experienced with large-scale software systems
- Strong experience in Python with a desire to learn new programming languages
- Familiarity with software collaboration tools (git, Jira, etc.)
- Good Linux knowledge
- Good understanding of math and ability to interpret research papers in the Machine Learning field ( Computer Vision)Experience on:
Experience working with two or more of the following
- RGBD sensors
- Technology type (Structure light, Stereo, ToF, etc.)
- Reconstruction algorithms (ICP, Volume integration, etc.)
- RGB sensors:
- Intrinsic and lens distortion calibration
- Extrinsic calibration
- Structure from motion (or visual odometry or visual SLAM)
- Machine learning algorithms for Computer Vision, datasets and infrastructure
- Inverse/Differential/Neural Rendering
Plus points for any of these
- Master’s or further education
- Experience with GPU Programming (CUDA, OpenCL)
- Experience with ROS
- Experience using machine learning platforms, tools and libraries (such as PyTorch,Tensorflow, Kubernetes, Docker, Azure, Google Cloud, etc.)
- Contributions to Open Source projects