Join Shield AI’s Hivemind SDK State Estimation & Vision team to build deep learning capabilities that help autonomous systems understand their motion and localize in the world when GPS is unavailable or unreliable.
You will work at the intersection of deep learning, 3D computer vision, and geometric estimation, developing learned components for vision-based navigation. You will own the model development pipeline—from selecting tools, defining annotation needs, and cleaning data through training, evaluation, integration support, and deployment recommendations.
Hands-on experience with Deep Learning and 3D computer vision and geometry is required; prior experience specifically in vision-based navigation is optional.
What you'll do:
- Develop and evaluate models for tasks such as feature detection and matching, visual correspondence, depth estimation, relative pose estimation, and image-to-map localization.
- Combine learned visual representations with geometric methods to improve localization accuracy, robustness, and recovery under challenging conditions.
- Own data preparation and supervision strategies, including dataset curation, annotation requirements, labeling tools, automated quality checks, and coverage analysis.
- Select and integrate deep learning tools and build reproducible training workflows, including experiment tracking, configuration management, and dataset and model versioning.
- Design evaluations that measure both model performance and downstream localization outcomes across changes in lighting, viewpoint, altitude, terrain, weather, and sensor characteristics.
- Analyze failures and use controlled experiments to prioritize improvements to data, supervision, models, and integration.
- Partner with state estimation engineers to integrate learned measurements and confidence estimates into VIO and terrain-relative navigation systems.
- Profile models against onboard compute, memory, and latency constraints, and work with deployment engineers on optimization and runtime validation.
- Deliver tested, documented components and interfaces for Hivemind SDK, collaborating with software, systems, and flight test teams.
Required qualifications:
- M.S. in Aerospace Engineering, Electrical Engineering, Robotics, Computer Science, or a related field; minimum 4+ years of related professional work experience with an M.S. degree, or 2+ years with a Ph.D.
- Hands-on experience designing, training, debugging, and evaluating models using PyTorch or an equivalent framework, including architecture selection, loss design, optimization, and augmentation that preserves geometric consistency.
- Strong foundations in camera models, coordinate transformations, projective geometry, and multi-view geometry, with practical experience in one or more fields: vision-based navigation, visual geolocation, Structure from Motion (SfM), SLAM, 3D reconstruction, depth estimation or similar fields. Expertise in every area is not required.
- Strong Python skills and experience writing maintainable, reusable software. Demonstrated ability to take a computer vision capability from problem definition and raw data through training, evaluation, and integration readiness.
- Experience building pipelines for sensor data ingestion, cleaning, filtering, deduplication, and dataset versioning.
- Ability to select and integrate development tools and build reproducible training workflows, including configuration management, experiment tracking, checkpointing, and GPU performance troubleshooting.
- Experience designing benchmarks, preventing data leakage across related sequences or locations, analyzing performance across operating conditions, and connecting model metrics to downstream geometric or localization accuracy.
- Ability to profile inference latency and memory use, document model interfaces and preprocessing, assess accuracy–compute tradeoffs, and advise deployment engineers on export, precision, and runtime optimization.
- Ability to communicate assumptions, experimental findings, and design tradeoffs clearly and translate research into working software.
Preferred qualifications:
- Experience with aerial imagery, geospatial data, elevation maps, or matching observations across viewpoint, lighting, season, or sensor modality
- Experience with model export, quantization, TensorRT, ONNX, or deployment on embedded compute platforms.
- Experience validating perception or robotics systems on physical platforms.
- Relevant publications, open-source contributions, or demonstrated delivery of production computer vision systems, familiar with methods including:
- feature correlation, correlation or cost volumes, and matching methods for correspondence, stereo, optical flow, or localization.
- learning priors over scene geometry, depth, motion, or appearance to improve estimation under sparse, ambiguous, or degraded observations.
- applying diffusion models or flow matching to computer vision, geometric inference, or conditional generation.
- Experience in aerospace and / or defense industry.
Skills Required
- M.S. in aerospace engineering, electrical engineering, robotics, computer science, or a related field, plus 4 or more years of related professional experience; alternatively, a Ph.D. with 2 or more years of related experience.
- Hands-on experience designing, training, debugging, and evaluating deep learning models using PyTorch or an equivalent framework.
- Strong knowledge of camera models, coordinate transformations, projective geometry, and multi-view geometry.
- Practical experience in vision-based navigation, visual geolocation, Structure from Motion, SLAM, 3D reconstruction, depth estimation, or a similar field.
- Strong Python skills and experience writing maintainable, reusable software.
- Experience taking computer vision capabilities from problem definition and raw data through training, evaluation, and integration readiness.
- Experience building sensor data pipelines for ingestion, cleaning, filtering, deduplication, and dataset versioning.
- Experience creating reproducible training workflows with configuration management, experiment tracking, checkpointing, and GPU performance troubleshooting.
- Experience designing benchmarks, preventing data leakage, analyzing performance across operating conditions, and connecting model metrics to localization accuracy.
- Ability to profile inference latency and memory use, document model interfaces and preprocessing, evaluate accuracy-compute tradeoffs, and advise on deployment optimization.
- Ability to communicate assumptions, experimental findings, and design tradeoffs clearly and translate research into working software.
- Experience with aerial imagery, geospatial data, elevation maps, or matching observations across viewpoints, lighting, seasons, or sensor modalities.
- Experience with model export, quantization, TensorRT, ONNX, or embedded compute platforms.
- Experience validating perception or robotics systems on physical platforms.
- Relevant publications, open-source contributions, or demonstrated delivery of production computer vision systems.
- Experience with feature correlation, cost volumes, and correspondence, stereo, optical flow, or localization methods.
- Experience learning priors over scene geometry, depth, motion, or appearance for degraded observations.
- Experience applying diffusion models or flow matching to computer vision, geometric inference, or conditional generation.
- Experience in the aerospace or defense industry.
What the Team is Saying
What We Do
At Shield AI, you won't wait years to see your work reach the field. You'll build hardware and software that operates in the real world right now, in the hands of the people who depend on it. Hivemind, our AI pilot, has been flying since 2018. It has flown more than 30 platforms, including an F-16, and it now sits under a U.S. Air Force production contract for Collaborative Combat Aircraft. When you write code or shape a system here, you contribute to technology with a proven flight record and a clear production future. V-BAT flies intelligence, surveillance, and reconnaissance missions with an operational record that stretches from Ukraine to the Indo-Pacific. It delivers eyes where they matter most, in the most demanding conditions on earth. The teams behind it watch their work get tested where the stakes are real. X-BAT takes its first flight this year. It's an AI-piloted fighter that needs no runway, built to operate where traditional aircraft can't. Join now and you help shape a program at its earliest, most formative stage. That's the kind of ground-floor work that defines a career. Do the most impactful work of your life, on problems that matter. Autonomy at this level asks a lot of you. You'll take on problems in perception, planning, and control that few teams anywhere are equipped to solve. You'll work across disciplines, from aerospace and robotics to machine learning and systems engineering, alongside people who hold themselves to an exacting standard and expect the same from you. Our mission is clear: protect service members and civilians with intelligent systems. That purpose runs through every decision, every design review, and every deployment. It's why the work here carries a weight you can feel. Ready to join our mission? Explore our open roles and find where you fit.
Why Work With Us
Founded in 2015 by a former Navy SEAL, Shield AI builds AI pilots and uncrewed aircraft. Veterans aren't an afterthought here, they're at every level. It's why the work carries weight: AI pilots and uncrewed aircraft flying real missions, from Ukraine to the Indo-Pacific, protecting service members and civilians.
Gallery
%203.jpg)
Shield AI Teams
.jpg)
Shield AI Offices
Hybrid Workspace
Employees engage in a combination of remote and on-site work.
