Robotics/Autonomy Engineer - Computer Vision
Knightwerx Inc.
Paradise Valley, United States of America
31 days ago
Role details
Contract type
Permanent contract Employment type
Full-time (> 32 hours) Working hours
Regular working hours Languages
English Experience level
SeniorJob location
Paradise Valley, United States of America
Tech stack
Computer Vision
C++
CMake
Nvidia CUDA
Computer Programming
Computer Engineering
Software Debugging
Field-Programmable Gate Array (FPGA)
Global Positioning Systems (GPS)
H.264/MPEG-4 AVC
Integrated Development Environments
Python
Network Protocols
Object Detection
OpenCV
Sensor Fusion
Serial Communications
Signal Processing
Software Engineering
Systems Integration
Video Codec
Visual Systems
High Efficiency Video Coding (HEVC)
Deep Learning
Audio Codec
GIT
RTSP
Containerization
Kubernetes
Information Technology
Build Tools
Hardware Acceleration
Feature Extraction
Software Version Control
Docker
Job description
- Knightwerx is seeking a highly skilled Robotics/Autonomy Engineer - Computer Vision to lead development and integration of advanced perception, vision-based navigation, and autonomy software for a small, unmanned electric aircraft. We operate in a fast-paced development environment that balances innovation and ingenuity with practicality and reliability. You'll collaborate with flight-software, aeromechanical, and avionics teams to deliver robust autonomy for GPS-denied, contested, and complex environments from prototype through production. The role emphasizes cutting-edge computer vision, sensor fusion, and real-time autonomy algorithms to enable resilient operations in austere conditions., * Design, develop, and optimize computer vision and ISP software for real-time robotic and UAV applications.
- Implement and maintain camera drivers, video pipelines, and hardware-accelerated vision algorithms.
- Integrate vision systems with navigation, control, and autonomy stacks.
- Ensure software is scalable, maintainable, and efficient across embedded and distributed platforms.
- Collaborate with hardware, systems, and autonomy engineers to deliver end-to-end solutions.
- Participate in documentation of design, implementation, and test procedures.
- Troubleshoot and debug system-level issues in camera and vision pipelines.
- Stay current with emerging CV/ML methods, hardware accelerators, and best practices.
Tasks
- Develop and optimize computer vision algorithms for perception, navigation, and target detection in GPS-denied and contested environments
- Integrate vision systems with autonomy software, including sensor fusion, SLAM, and obstacle avoidance
- Select, configure, and test vision sensors and compute payloads to support autonomous behaviors
- Implement and validate real-time autonomy features using vision-based inputs and multi-sensor data
- Ensure perception and autonomy software is scalable, maintainable, and efficient for prototype through production
- Participate in rigorous field testing, data collection, and refinement of vision/autonomy performance
- Document software design, algorithms, and test procedures for technical teams and stakeholders
Requirements
- Bachelor's or higher degree in Computer Engineering, Electrical Engineering, Computer Science, Robotics, or a related discipline.
- 5+ years of relevant industry experience in computer vision, robotics, or embedded systems.
- Proven experience developing image signal processing (ISP) and computer vision (CV) software.
- Hands-on experience with MIPI Camera Serial Interface (CSI) and writing drivers for image sensors.
- Experience integrating and operating camera systems in UAVs or other autonomous platforms.
- Knowledge of video codecs (H.264/H.265) and network protocols for video transmission (RTSP, MPEG-TS).
Attributes
- Effective collaborator in cross-functional team environments.
- Open to feedback and committed to continuous improvement.
- Innovative, hands-on, and practical in problem solving.
- Multi-disciplinary mindset with strong engineering analysis skills.
- Goal-driven, resilient, and accountable throughout the design process, * Strong understanding of image formation, filtering, feature extraction, segmentation, optical flow, object detection, tracking, and recognition.
- Experience with camera calibration (intrinsic/extrinsic) and time synchronization of multi-sensor data.
- Proficiency with OpenCV, GStreamer, and V4L2.
- Practical experience with hardware acceleration (CUDA, SIMD, Vulkan, etc.).
- Familiarity with Nvidia Jetson platforms, FPGAs, and VPUs (Intel Movidius, Coral TPU).
- Experience with deep learning-based CV methods (CNNs, transformers, object detection/segmentation frameworks such as YOLO, Faster R-CNN, Mask R-CNN, DETR, SAM, etc.).
- Knowledge of classical CV methods (SIFT, SURF, ORB, HOG, Harris/FAST/ORB keypoints).
- Understanding of image/video stabilization, SLAM, and 3D reconstruction fundamentals.
- Experience with containerization (Docker) and container orchestration.
- Proficiency with version control systems (Git) and build tools (CMake).
- Strong programming skills in C++, Python, and/or Rust., * Must have US citizenship
- On-site, collaborative work environment