Staff Deep Learning Engineer State Estimation

You will develop, train, evaluate, and integrate deep-learning components for vision-based navigation and localization. You will curate data, define annotation strategies, create reproducible training workflows, analyze model failures, and assess deployment constraints. You will work with state-estimation engineers to integrate learned measurements into navigation systems and deliver documented SDK components.

Responsibilities

• Develop and evaluate models for visual correspondence, depth estimation, pose estimation, and image-to-map localization
• Combine learned visual representations with geometric methods
• Own dataset curation, annotation requirements, labeling tools, and quality checks
• Build reproducible training workflows with experiment tracking and versioning
• Design evaluations for model and localization performance
• Analyze failures and prioritize improvements to data, supervision, models, and integration
• Integrate learned measurements into VIO and terrain-relative navigation systems
• Profile models against compute, memory, and latency constraints
• Deliver tested and documented Hivemind SDK components

Requirements

• M.S. in a related field with 4+ years of professional experience, or a Ph.D. with 2+ years
• Deep-learning model design, training, debugging, and evaluation experience using PyTorch or an equivalent framework
• Knowledge of camera models, coordinate transformations, projective geometry, and multi-view geometry
• Experience in vision-based navigation, visual geolocation, SfM, SLAM, 3D reconstruction, depth estimation, or similar fields
• Python software-development skills
• Experience with sensor-data pipelines, data cleaning, filtering, deduplication, and dataset versioning
• Experience with reproducible training workflows and GPU troubleshooting
• Experience designing benchmarks and evaluating latency, memory, and accuracy-compute tradeoffs

Benefits

• Bonus
• Equity