Senior Engineer, Computer Vision (C++) (R5195)

About the role

Shield AI is a venture-backed defense-tech company with the mission of protecting service members and civilians with intelligent systems. Its products include Hivemind autonomy software, V-BAT and X-BAT aircraft, and Aechelon simulation and synthetic reality technologies. With offices and facilities across the U.S., Europe, the Middle East, and Asia-Pacific, Shield AI’s technology actively supports operations worldwide. For more information, visit www.shield.ai. Follow Shield AI on LinkedIn, X, Instagram, and YouTube.

Job Description:
This role is for a Computer Vision C++ Engineer to support the development of real-time perception capabilities for Shield AI's autonomous systems.
The Computer Vision Engineer will be responsible for designing, developing, and integrating advanced computer vision algorithms into high-performance C++ software pipelines. The role will focus on building custom perception capabilities from the ground up, with an emphasis on real-time performance, reliability, and deployment in edge compute environments. This position is required to increase the team's capacity and technical depth in real-time computer vision, image processing, and applied machine learning.
The successful candidate will bring strong C++ software engineering skills, experience developing high-performance or real-time systems, and a deep understanding of computer vision fundamentals. They should be capable of translating research concepts into deployable software and comfortable working on bespoke algorithms rather than relying only on existing libraries. Experience with areas such as object detection, image classification, target recognition, semantic segmentation, feature extraction, object tracking, video analytics, dataset curation, model evaluation, or deployment of trained perception models would be highly valuable.
The role will also support the development and integration of learned perception models into real-time computer vision pipelines. This may include adapting detection, classification, recognition, or segmentation models for operational imagery; improving model performance across varied lighting, viewpoint, background, and environmental conditions; evaluating false positives and false negatives; and working with representative datasets to improve robustness. Familiarity with combining learned models with classical computer vision techniques, optimizing inference for edge deployment, and integrating model outputs into C++ perception systems would be beneficial. Candidates with a Master's or PhD in Computer Science, Engineering, Robotics, Computer Vision, Machine Learning, or a related field would be well aligned with the technical needs of the team, though strong applied industry experience is also highly relevant.