Path Robotics
Software Simulation Engineer, Sensor Rendering
Columbus, OhiomidAdded today
About this role
Path Robotics seeks a Software Simulation Engineer to design and implement photorealistic sensor simulation pipelines for robot perception model training. You'll develop physics-based rendering for 2D/3D sensors, create synthetic datasets with domain randomization, and ensure sim-to-real transfer for AI-driven welding robots.
What you'll do
- Implement and validate physics-based sensor simulation models (structured light, depth, RGB, stereo) in NVIDIA Isaac Sim, Blender, or Unreal Engine
- Build photorealistic scene rendering pipelines with accurate material properties, sensor placement, and robot trajectories
- Develop synthetic data generation pipelines producing annotated ground-truth (point clouds, depth maps, segmentation masks) at scale
- Implement domain randomization strategies to improve sim-to-real transfer for perception models
- Collaborate with perception teams to ensure rendered outputs meet dataset requirements
- Lead sensor rendering strategy design, validation frameworks, and 3D asset/environment pipeline management (Senior level)
What they're looking for
- Python (production-grade simulation tooling)
- NVIDIA Isaac Sim, Unreal Engine, Blender, or Gazebo
- Physically Based Rendering (PBR) and 3D asset formats (URDF, SDF, USD)
- Synthetic data pipeline design and domain randomization
- CAD-to-simulation workflows and material authoring
- Sensor simulation and characterization
- Generative AI (diffusion models) for synthetic data
- Physics-based simulation and ray tracing
Opens the official application on the employer’s site. No login required.
Path Robotics
Path Robotics develops autonomous robotic welding systems with adaptive motion planning and AI-driven capabilities for manufacturing. The company is hiring welding engineers, mechanical engineers, machine learning engineers, and technical marketing engineers to advance its mobile robotic welding solutions.
- Website
- pathrobotics.com
Likely interview questions
- Describe your experience building synthetic data generation pipelines—what sensors have you simulated and what domain randomization strategies did you employ?
- How would you approach validating that synthetic sensor data from simulation matches real-world sensor behavior for training perception models?