Software Engineer I, Perception (New Grad)
This entry-level Software Engineer role focuses on developing hybrid perception systems for autonomous spacecraft by integrating classical computer vision techniques with modern deep learning. The engineer will implement and optimize multi-object tracking algorithms, train neural networks, and deploy perception pipelines on space-qualified edge hardware to enable spacecraft navigation and threat discrimination. The position offers hands-on experience with state estimation, coordinate transformations, synthetic data generation, and real-time algorithm deployment in a mission-critical space environment.
About Careertakes
👉 Important disclosure: Careertakes is a third-party recruiting platform supporting this hiring process. If selected, you will be employed directly by our client, Engineering.
Applicants for this role may also receive access to additional matched opportunities through the Careertakes platform.
Position overview
Confidential Client is hiring an entry-level Software Engineer I, Perception (New Grad) to work on hybrid perception systems for autonomous spacecraft. This is a 3-month temporary engagement with potential to convert to regular employment based on performance and business need. The role blends classical computer vision, estimation theory, and modern deep learning — implementing tracking pipelines, coordinate transforms to orbital frames, training models on synthetic space imagery, and deploying efficient inference on flight-grade hardware.
Key responsibilities
- Implement classical tracking algorithms: Extended Kalman Filters, Hungarian algorithm for data association, and track management logic (tentative/confirmed/coasted tracks)
- Train and evaluate neural networks for detection and classification (e.g., YOLO, ResNet variants) and develop learned appearance features for re-identification
- Build hybrid perception pipelines: neural-network detections → classical tracking → coordinate transformations → angle-only measurements for navigation
- Develop image-processing chains: hot-pixel filtering, adaptive thresholding, centroiding, connected-component analysis, and star-catalog matching
- Deploy and optimize models to edge/flight hardware: INT8 quantization, ONNX Runtime/TensorRT integration, and performance tuning for space-qualified processors
- Implement coordinate transformations: pixel → camera → body → Earth-Centered Inertial (ECI), accounting for lens distortion and attitude uncertainty
- Generate synthetic training datasets using rendering tools (Blender/Unreal) with domain randomization for rare scenarios
- Validate end-to-end performance with software-in-the-loop, processor-in-the-loop, and hardware-in-the-loop testing using real camera feeds
Minimum qualifications
- Currently pursuing or recently completed a Bachelor’s or Master’s degree in Computer Science, Electrical Engineering, Robotics, Aerospace Engineering, or a closely related technical field
- Coursework or strong interest in computer vision and estimation theory (or clear willingness to learn both)
- Proficiency in Python; some exposure to C++ (training provided)
- Familiarity with either classical tracking methods (Kalman filters, data association) OR deep-learning model training (PyTorch)
- Solid understanding of linear algebra, probability, and coordinate transformations
- Ability to read and implement algorithms from robotics (ICRA/IROS) and ML (CVPR/NeurIPS) literature
- Strong debugging skills for numerical stability, tracking failures, and model issues
- U.S. citizenship (required for facility access and government contract compliance)
Preferred skills and experience
- Experience with Extended Kalman Filters, multi-object tracking, or state estimation
- Familiarity with object detection and classification workflows (YOLO, Faster R-CNN, ResNet)
- Understanding of camera intrinsics/extrinsics, quaternions, rotation matrices, and orbital frames (ECI/LVLH/RIC)
- Experience optimizing models for edge deployment (INT8/FP16 quantization, ONNX, TensorRT)
- Hands-on experience with OpenCV and classical image-processing pipelines
- Coursework or projects in optimal estimation, sensor fusion, or probabilistic robotics
- Prior work generating synthetic training data and using domain randomization
- Experience deploying algorithms to embedded systems (Jetson, ROS) or debugging visual systems in real-world conditions
- Exposure to multi-modal sensor fusion (camera + IMU, camera + lidar)
Compensation
- Base salary (Denver, CO): $75,000 per year
Your actual base salary will be determined case-by-case and may vary by job-related knowledge, skills, education, location, and experience.
Work location & logistics
- Primary work location for this posting: Denver, CO (Centennial-area facilities)
- This position requires onsite or near-site presence for facility access, testing, and hardware-in-the-loop work
- This role may include physical demands related to lab work, including sitting, standing, lifting, or working with cameras and test rigs
Security & export compliance
To comply with U.S. Government space-technology export regulations (including ITAR), candidates must be U.S. citizens, lawful permanent residents, protected individuals as defined by 8 U.S.C. 1324b(a)(3), or otherwise eligible to obtain required authorizations from the U.S. Department of State. Facility access and certain contracts require these statuses.
Equal Opportunity & Hiring Transparency
Careertakes and our client are Equal Opportunity Employers committed to building a diverse and inclusive workforce. We prohibit discrimination or harassment of any kind. To support a fair and efficient hiring process, AI tools may be used to assist with application review or resume screening. These tools do not replace human decision-making. Final hiring decisions are made by people.
If you have questions about how your data is used, please contact us directly.
Negotiate a higher salary! Check the salary ranges for this job type in your area.
View My Salary Range