Observable Space
Computer Vision Engineer
About this role
Join a team of experienced engineers and scientists to develop cutting-edge computer vision solutions for space domain awareness and satellite tracking. You'll own end-to-end image processing pipelines, train advanced deep learning models, and lead research projects that bridge classical vision techniques with modern AI.
What you'll do
- Research and implement latest advances in space domain awareness, photometry, and image processing techniques
- Develop and deploy proof-of-concept solutions collaborating with software teams based on state-of-the-art research
- Train and customize deep learning models using architectures like U-Net, Vision Transformers, and ResNet
- Own image processing pipelines from sensor readout through cloud data warehouse publication
- Design and generate synthetic data for algorithm testing and validation
- Lead multidisciplinary research projects and communicate findings to technical and non-technical audiences
What they're looking for
- Computer vision and image processing
- C++ or C programming in production environments
- PyTorch or TensorFlow for machine learning
- OpenCV and classical vision techniques
- Deep learning model architecture and training
- Space domain awareness (SDA) and satellite tracking
- Mathematical and computational problem-solving
- Data pipeline development and cloud integration
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Observable Space
Observable Space builds advanced telescope and observatory systems for space-based and terrestrial applications, developing integrated hardware and software solutions for next-generation space infrastructure. The company is hiring electrical engineers, mechanical engineers, photonics specialists, test engineers, and full-stack software engineers to design, validate, and optimize these complex systems.
View all jobs at Observable SpaceLikely interview questions
- Walk us through a complex computer vision project you owned end-to-end—what were the biggest technical challenges?
- How have you approached training and customizing deep learning models for specific image processing tasks?