Staff Deep Learning Engineer, State Estimation

This is a fully remote position, open to applicants in United States.

📋 Description

• Develop and assess deep learning models aimed at feature detection and matching, visual correspondence, depth estimation, relative pose estimation, and image-to-map localization.

• Integrate learned visual representations with geometric techniques to enhance localization accuracy, robustness, and recovery.

• Manage data preparation and supervision strategies, including dataset curation, annotation requirements, labeling tools, automated quality checks, and coverage analysis.

• Choose and incorporate deep learning tools while establishing reproducible training workflows that include experiment tracking, configuration management, and dataset/model versioning.

• Create evaluations for model performance and downstream localization results across various conditions such as lighting, viewpoint, altitude, terrain, weather, and sensor variations.

• Evaluate failures and conduct controlled experiments to prioritize enhancement areas.

• Collaborate with state estimation engineers to fuse learned measurements and confidence estimates into VIO and terrain-relative navigation systems.

• Assess models against onboard computing, memory, and latency limitations.

• Collaborate with deployment engineers to optimize and validate runtime performance.

• Provide tested and well-documented Hivemind SDK components and interfaces.

• Work in cooperation with software, systems, and flight test teams.

⛳️ Requirements

• M.S. in Aerospace Engineering, Electrical Engineering, Robotics, Computer Science, or a closely related field.

• At least 4+ years of relevant professional experience with an M.S. degree, or 2+ years with a Ph.D.

• Practical experience in designing, training, debugging, and evaluating models using PyTorch or a similar framework.

• Familiarity with architecture selection, loss design, optimization, and augmentation techniques that maintain geometric consistency.

• Strong foundation in camera models, coordinate transformations, projective geometry, and multi-view geometry.

• Hands-on experience in vision-based navigation, visual geolocation, Structure from Motion (SfM), SLAM, 3D reconstruction, depth estimation, or related disciplines.

• Proficient in Python with experience in writing maintainable, reusable software.

• Experience progressing computer vision capabilities from problem definition and raw data to training, evaluation, and integration readiness.

• Background in building pipelines for sensor data processing, including ingestion, cleaning, filtering, deduplication, and dataset versioning.

• Capability to choose and integrate development tools and create reproducible training workflows.

• Experience with configuration management, experiment tracking, checkpointing, and troubleshooting GPU performance.

• Skilled in designing benchmarks, preventing data leakage, analyzing performance across different operational conditions, and connecting model metrics to downstream geometric or localization accuracy.

• Ability to profile inference latency and memory usage, document model interfaces and preprocessing, assess accuracy–compute tradeoffs, and provide advice on deployment optimization.

• Strong communication skills to articulate assumptions, experimental results, and design tradeoffs clearly, as well as translating research into functional software.

• All offers are contingent upon a cleared background and potential reference checks.

• Preferred: experience with aerial imagery, geospatial data, elevation maps, or cross-condition/multimodal matching.

• Preferred: familiarity with model export, quantization, TensorRT, ONNX, or embedded computing.

• Preferred: experience in validating perception or robotics systems on physical platforms.

• Preferred: relevant publications, open-source contributions, or production computer vision systems.

• Preferred: experience with feature correlation, cost volumes, matching methods, learned geometry/depth/motion/appearance priors, diffusion models, or flow matching.

• Preferred: experience in the aerospace and/or defense industry.

• Eligibility to work in the United States / authorization to work in the United States as stated in the application form.

• Potential access to export-controlled information requiring U.S. citizenship, U.S. lawful permanent residency, protected individual status, or other qualifying criteria.

🏝️ Benefits

• Bonus

• Benefits

• Equity

• Temporary benefits package applicable after 60 days of employment (for temporary employees)

• Full-time regular employee offer package

• Cleared background and possible reference check contingent offer process