Robotics Perception and Navigation Engineer AstraQua

Location: Los Angeles, CA or Louisville, KY

About the work

Develop perception and localization capabilities for robots operating in changing environments. Connect detections, tracks, position estimates and system-health information to shared mission awareness, keeping state estimation, route planning and vehicle control responsibilities clear.

What you will do

• Build and evaluate object detection, tracking, visual perception and sensor-fusion components using repeatable datasets and quantitative metrics.
• Define coordinate frames, calibration procedures, timestamps and interfaces for perception and localization outputs.
• Develop navigation-related interfaces that distinguish estimated state, planned routes and low-level vehicle control.
• Evaluate behavior under sensor degradation, uncertain observations and constrained communications in simulation and approved hardware trials.
• Work with Astra Sense/AQFM interfaces so health, usable capability and uncertainty can inform planning or replanning within defined authority.
• Support shared observations and multi-robot integration with explicit data formats, confidence measures and handling of stale or missing data.
• Maintain experiment logs, known failure cases, regression tests and clear distinctions between simulated and physical results.

What you bring

• Practical computer vision, robotics or state-estimation experience with Python or C++.
• Ability to work with sensor data, coordinate frames, calibration and quantitative evaluation.
• Experience with reproducible experiments and safe, documented robot testing.

Useful additional experience

ROS 2, Gazebo, visual odometry, SLAM, depth cameras, LiDAR, resource-constrained inference or multi-robot data exchange.

First 90 days: scope to agree

Agree a scoped first-90-day objective: a repeatable perception or localization demonstration with documented test conditions, accuracy measures, degraded-sensor cases, known failures and integration interfaces. Hardware trials depend on approved equipment and test procedures.

About Astra Qua

Astra Qua is developing a modular autonomy architecture with AQFM as its shared intelligence foundation. Specialized agents contribute perception, reasoning, health and coordination. Astra Sense is the health-intelligence agent, with electrified aviation as an initial research application; it connects condition and remaining capability with mission decisions. Our approach to safe AI emphasizes defined operating boundaries, deterministic safety controls, operator authority and behavior designed for verification and validation.