Software Engineer - Perception (Fallback Stack)

About the role

As a Perception Software Engineer on the Autonomy team, you will develop the perception stack for Level‑4 autonomous trucks that operate at highway speeds. You will own the end‑to‑end pipeline, from model design and training to on‑vehicle deployment and safety validation.

Key responsibilities

• Design, train and deploy deep‑learning models for 3‑D object detection using LiDAR, camera and radar data.
• Build multi‑sensor fusion architectures that combine independent detection and classification streams.
• Identify and characterize perception failure modes, create targeted evaluation sets and improve system‑level metrics.
• Develop and operate the data engine for shadow‑mode comparison, automated data mining and continuous retraining loops.
• Contribute to camera‑ and LiDAR‑based localization under degraded conditions.
• Run the full safety validation pipeline, including simulation, closed‑course testing and formal sign‑off before public‑road deployment.

Required profile

• Bachelor’s or Master’s degree in Computer Science, Robotics, Electrical Engineering or a related field.
• 5+ years of professional experience building ML‑based perception systems for autonomous vehicles.
• Proven experience with state‑of‑the‑art 3‑D detection, BEV representations and multi‑object tracking.
• Hands‑on experience with safety‑critical software development and validation processes.
• Ability to collaborate daily with behavior, planning, systems, safety and validation engineers.

Required skills

• Python and C++ programming.
• Deep‑learning frameworks such as PyTorch or TensorFlow.
• LiDAR, radar and camera sensor processing.
• Multi‑sensor fusion and BEV (bird‑eye‑view) representations.
• State estimation and multi‑object tracking algorithms.
• Data pipeline development, shadow‑mode comparison and automated data mining.
• Simulation and closed‑course testing tools for safety validation.