What you'll do:
- Serve as the technical authority for computer vision capabilities within our perception stack, driving technical decisions and ensuring robust design and implementation.
- Architect and develop core video and image processing C++ software libraries, released as part of our software products to external customers.
- Implement out-of-the-box computer vision capabilities for applications such as object detection, visual place recognition, visual odometry, and more.
- Advanced the state of the art in computer vision to enable advanced autonomy behaviors for commercial and defense applications
- Validate computer vision capabilities through various testing modalities (e.g., digitalsimulation, software-in-the-loop, hardware-in-the-loop, and flight testing)
- Collaborate with the product development team to shape the technical roadmap for perception
- Engage with internal and external customers to inform requirements for new features
- Enhance the performance of an exceptionally talented perception team by maintaininghigh standards of technical rigor, balancing development speed with product quality.
- Mentor and guide less experienced engineers, fostering technical excellence and sharing domain knowledge across the team.
Required Qualifications:
- Typically requires a minimum of 10 years of related experience with a Bachelor’s degree; or 9 years with a Master’s degree; or 7 years with a PhD; or equivalent work experience.
- Demonstrated excellence in designing and developing scalable, extensible C++ video and image processing software for CPU and GPU systems in Linux environments, preferably for autonomous systems.
- Extensive experience working with open-source video and image processing libraries, such as GStreamer and OpenCV.
- Proven expertise in C++ software architecture design patterns and their practical implementation.
- Strong knowledge of video encoding standards (e.g., H.264 and H.265) and their application.
- Experience developing video or image processing algorithms for electro-optional sensors.
- Strong Git and Linux development skills, along with modern software development practices (e.g., CI/CD, test-driven development).
- A track record of technical leadership, with the ability to set and maintain high standards, guide teams through complex technical challenges, and collaborate effectively.
Preferred Qualifications:
- Hands-on experience working with EO/IR sensor hardware used for defense applications
- Demonstrated excellence in designing and developing scalable, extensible C++ video and image processing software for CPU and GPU systems in Linux environments, preferably for autonomous systems.
- Extensive experience working with open-source video and image processing libraries, such as GStreamer and OpenCV.
- Strong knowledge of video encoding standards (e.g., H.264 and H.265) and their application.
Why join us?
- At Shield AI, you will work on cutting-edge technology that pushes the boundaries of autonomous systems. This role offers the opportunity to lead the technical direction of a critical component in our perception stack while collaborating with a team of talented engineers and researchers. Your work will have a direct impact on enabling advanced autonomy for defense and beyond.
Top Skills
What We Do
Shield AI is building the world's best AI pilot. Our Hivemind autonomy stack is the first and only autonomous AI Pilot, deployed in combat since 2018. Hivemind enables intelligent teams of aircraft to perform missions ranging from room clearance, to penetrating air defense systems, and dogfighting F-16s.
Why Work With Us
What makes Shield AI special is our people. We unlock the power of autonomy, and in the face of overwhelming odds and challenges, we find ways to win and make a difference for our customers. We bring together software, AI, and aerospace engineering disciplines to deploy the most intelligent aviation capabilities in the world.
Gallery
