Staff Deep Learning Engineer, State Estimation (R5785)

Shield AI is a defense-tech company dedicated to protecting service members and civilians through the development of intelligent systems. As a Staff Deep Learning Engineer, you will join the Hivemind SDK State Estimation & Vision team to build advanced deep learning capabilities that enable autonomous systems to navigate and localize effectively in GPS-denied or unreliable environments.

Key responsibilities

• Develop and evaluate models for feature detection, visual correspondence, depth estimation, and image-to-map localization.
• Combine learned visual representations with geometric methods to enhance localization accuracy and robustness.
• Own the end-to-end data preparation strategy, including dataset curation, annotation requirements, and automated quality checks.
• Design reproducible training workflows and experiment tracking systems to optimize model performance.
• Collaborate with state estimation engineers to integrate learned measurements into VIO and terrain-relative navigation systems.
• Profile models against onboard compute, memory, and latency constraints to ensure efficient deployment.

Requirements

• M.S. in Aerospace, Electrical Engineering, Robotics, Computer Science, or a related field with 4+ years of experience, or a Ph.D. with 2+ years of experience.
• Hands-on experience designing, training, and evaluating models using PyTorch or equivalent frameworks.
• Strong foundation in camera models, coordinate transformations, and multi-view geometry.
• Practical experience in vision-based navigation, SLAM, Structure from Motion, or 3D reconstruction.
• Proficiency in Python and experience building maintainable, reusable software pipelines.
• Ability to analyze performance across diverse operating conditions and translate research into production-ready software.

What we offer

• Opportunity to work at the intersection of deep learning, 3D computer vision, and geometric estimation.
• Impactful work on autonomous systems that support critical operations worldwide.
• Collaborative environment working alongside software, systems, and flight test teams.
• Access to complex challenges involving aerial imagery, geospatial data, and embedded compute platforms.