3 days ago
Base Salary
$200k - $300k/yr
Responsibilities
- Develop and evaluate deep learning models for feature detection and matching, visual correspondence, depth estimation, relative pose estimation, and image-to-map localization.
- Combine learned visual representations with geometric estimation methods to improve localization accuracy, robustness, and recovery.
- Own data preparation and supervision strategies, including dataset curation, annotation requirements, labeling tools, quality checks, and coverage analysis.
- Select and integrate deep learning tools and build reproducible training workflows with experiment tracking, configuration management, and dataset and model versioning.
- Design evaluations across lighting, viewpoint, altitude, terrain, weather, and sensor variations, and connect model metrics to downstream localization outcomes.
- Analyze failures and prioritize improvements to data, supervision, models, and system integration.
- Partner with state estimation engineers to integrate learned measurements and confidence estimates into VIO and terrain-relative navigation systems.
- Profile models for onboard compute, memory, and latency constraints and support deployment optimization and runtime validation.
- Deliver tested and documented components and interfaces for the Hivemind SDK in collaboration with software, systems, and flight test teams.
Requirements
- M.S. in aerospace engineering, electrical engineering, robotics, computer science, or a related field with at least 4 years of related professional experience, or a Ph.D. with at least 2 years of related experience.
- Hands-on experience designing, training, debugging, and evaluating models with PyTorch or an equivalent framework, including architecture selection, loss design, optimization, and geometry-consistent augmentation.
- Strong knowledge of camera models, coordinate transformations, projective geometry, and multi-view geometry, with practical experience in areas such as vision-based navigation, visual geolocation, SfM, SLAM, 3D reconstruction, or depth estimation.
- Strong Python skills and experience developing maintainable, reusable software across the computer vision lifecycle from problem definition and raw data through integration readiness.
- Experience building sensor-data pipelines for ingestion, cleaning, filtering, deduplication, and dataset versioning.
- Experience building reproducible training workflows, troubleshooting GPU performance, and using configuration management, experiment tracking, and checkpointing.
- Experience designing benchmarks, preventing data leakage, analyzing performance across operating conditions, and connecting model metrics to geometric or localization accuracy.
- Experience profiling inference latency and memory, documenting model interfaces and preprocessing, evaluating accuracy-compute tradeoffs, and advising on deployment optimization.
- Preferred qualifications include experience with aerial imagery, geospatial data, elevation maps, model export, quantization, TensorRT, ONNX, embedded compute, physical-platform validation, relevant publications, open-source contributions, production computer vision systems, diffusion models, flow matching, or aerospace and defense.
- Ability to communicate assumptions, experimental findings, and design tradeoffs clearly and translate research into working software.
Benefits
- Full-time regular employees receive bonus, benefits, and equity in addition to pay within the listed range.
- Temporary employees receive a temporary benefits package applicable after 60 days of employment.
- Offers are contingent on a cleared background and possible reference check.
- Military fellows and part-time employees are not eligible for benefits.
Categories
ML EngineeringRobotics
About Shield AI
Shield AI builds autonomous systems for military and national security customers, combining its Hivemind autonomy software with V-BAT and X-BAT unmanned aircraft and Aechelon simulation technologies. The privately held company sells hardware, software, and related services to U.S. and allied defense agencies. Founded in 2015 and headquartered in San Diego, it operates across the U.S., Europe, the Middle East, and Asia-Pacific, and its technology is used in operational deployments.