Staff DL Engineer - 3D Vision & Localization

Remote; San Francisco (CA); On-site; USD 190,000 - 290,000; Full time

Job summary

Shield AI, a defense-tech company with global reach, seeks an expert to advance Hivemind SDK state estimation and vision. You will lead deep learning for motion understanding and GPS-denied localization, bridging perception and geometric estimation across flight teams.

You will own data curation, tool selection, training workflows, and evaluative metrics, delivering reusable components for VIO and terrain-relative navigation, optimized for onboard compute and latency constraints.

Qualifications

• MS in a related field with 4+ years of work experience, or PhD with 2+ years.
• Hands-on PyTorch experience: training, debugging, and evaluation with geometric consistency.
• Strong foundations in camera models, coordinate transformations, and multi-view geometry.

Responsibilities

• Develop and evaluate models for feature detection, matching, and depth estimation.
• Combine learned representations with geometric methods for localization accuracy.
• Own data preparation, annotation needs, labeling tools, and quality checks.
• Build reproducible training workflows with experiment tracking and versioning.
• Design evaluations across lighting, viewpoints, altitude, and terrain changes.
• Analyze failures and prioritize data- and model-improvement experiments.
• Collaborate with state estimation engineers to integrate measurements into VIO/navigation.
• Profile models for onboard compute and memory, aiding deployment optimization.

Skills

PyTorch

Python

Geometry

SLAM

3D vision

Dataset versioning

Experiment tracking

Education

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

Ph.D. preferred or 2+ years with PhD

Tools

TensorRT

ONNX

CUDA

GPU profiling

Job description

Shield AI, a defense-tech company with global reach, seeks an expert to advance Hivemind SDK state estimation and vision. You will lead deep learning for motion understanding and GPS-denied localization, bridging perception and geometric estimation across flight teams.

You will own data curation, tool selection, training workflows, and evaluative metrics, delivering reusable components for VIO and terrain-relative navigation, optimized for onboard compute and latency constraints.