Senior / Staff 3D Engine Software Engineer - Simulation

The Zoox 3D Sensor Simulation team’s work is at the core of creating in-the-loop simulation and high fidelity synthetic data for training and testing autonomous vehicle AI. We are looking for a 3D Engine professional who spans both modern 3DGS techniques and traditional 3D graphics, including ray tracing and PBR rendering.

This role lies at the heart of 3D simulation at Zoox, ranging from cinema-quality offline rendering for software-in-the-loop (SIL) simulation, to optimized realtime 3D graphics for hardware-in-the-loop (HIL) simulation. With sensor simulation (cameras, lidar, and radar,), you’ll enable the Zoox robotics autonomy stack to learn, improve, and enhance the mobility of humans.

In this role, you will:

• Design, implement, and validate 3D rendering software for sensor simulation deployed in autonomous vehicle (AV) simulation pipelines.

• Collaborate with Synthetic Data and HIL Sim teams to develop rendering novel applications that combine 3DGS and polygonal mesh assets.

• Optimize performance and realism of realtime 3D sensor simulation, including cameras, lidar, and radar.

• Partner with Sim V&V engineers to improve metrics ranging from individual sensor fidelity to real-world AV safety reports.

• Lead 3D simulation engineers and establish best practices to steadily improve trustability and test coverage of SIL/HIL simulation use cases.

Qualifications:

• 2+ years of prior experience as a Technical Lead

• 7+ years of experience developing C++, Python, and GPU programming

• Experience integrating 3DGS implementations with traditional 3D graphics rendering

• Solid understanding of high performance real time simulation pipelines

Bonus Qualifications:

• Expertise with GPU programming, such as Compute shaders or CUDA

• Experience with sensor calibration, including cameras, lidar, and/or radar

• Experience with verification and validation (V&V) for autonomous systems

• Prior experience developing autonomy in AVs or other robotics and computer vision