Staff Deep Learning Engineer, State Estimation (R5785)

Remote · USD 200,000-300,000 / year · 2+ years experience · Remote · Posted Sep 26, 2026

At a glance

The Staff Deep Learning Engineer will join the Hivemind SDK State Estimation & Vision team to develop deep learning capabilities for autonomous systems.
The role focuses on enabling systems to understand motion and localize in GPS-denied or unreliable environments using 3D computer vision and geometric estimation.
You will own the full model development pipeline, from data curation and training to integration and deployment.

Develop and evaluate models for feature detection, visual correspondence, depth estimation, relative pose estimation, and image-to-map localization.
Combine learned visual representations with geometric methods to improve localization accuracy and robustness.
Own data preparation and supervision strategies, including dataset curation, annotation, and quality checks.
Select and integrate deep learning tools and build reproducible training workflows.
Design evaluations to measure model performance and downstream localization outcomes across varying environmental conditions.
Analyze failures and conduct controlled experiments to prioritize improvements.
Partner with state estimation engineers to integrate learned measurements into VIO and terrain-relative navigation systems.
Profile models against onboard compute, memory, and latency constraints.
Work with deployment engineers on optimization and runtime validation.
Deliver tested, documented components and interfaces for the Hivemind SDK.

M.S. in Aerospace Engineering, Electrical Engineering, Robotics, Computer Science, or a related field.
Hands-on experience designing, training, debugging, and evaluating models using PyTorch or an equivalent framework.
Strong foundations in camera models, coordinate transformations, projective geometry, and multi-view geometry.
Practical experience in one or more fields: vision-based navigation, visual geolocation, SfM, SLAM, 3D reconstruction, or depth estimation.
Strong Python skills and experience writing maintainable, reusable software.
Experience building pipelines for sensor data ingestion, cleaning, filtering, and dataset versioning.
Ability to select and integrate development tools and build reproducible training workflows.
Experience designing benchmarks and analyzing performance across operating conditions.
Ability to profile inference latency and memory use and assess accuracy-compute tradeoffs.
Ability to communicate assumptions, experimental findings, and design tradeoffs clearly.

Prior experience specifically in vision-based navigation.
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 or open-source contributions.
Familiarity with feature correlation, cost volumes, and matching methods.
Familiarity with learning priors over scene geometry, depth, motion, or appearance.
Experience applying diffusion models or flow matching to computer vision or geometric inference.