Principal Perception Architect - Detection and Fusion
AI summary of the role
Principal Perception Architect owning the modular perception ML, sensor fusion, object tracking/persistence, and 3D mapping architecture for autonomous construction machines.
What you’ll do
- Define modular perception ML architecture for camera-based detection, drivable area understanding, ground plane segmentation, and 4D radar-aided perception.
- Own sensor fusion architecture across camera, lidar, 4D radar, IMU, GNSS, and machine state data.
- Define object tracking and persistence architecture including association, lifecycle, occlusion handling, and cross-machine representation.
- Own 3D mapping architecture including local scene representation, local-to-global alignment, and persistent world representation.
What you’ll bring
- Strong experience with modular perception ML and sensor fusion for autonomous vehicles and robotics.
- Hands-on experience with camera images, lidar and 4D radar point clouds, IMU, GNSS, and machine state data in real perception systems.
- Solid understanding of object detection, drivable area understanding, ground plane segmentation, object tracking and fusion, and 3D mapping.
- Ability to work cross-functionally with edge platform, robotics and simulation teams.
Technologies
perception ML · sensor fusion · camera · lidar · 4D radar · IMU · GNSS · object tracking · 3D mapping · autonomy
About Caterpillar Inc.
Builds construction/mining equipment, engines, turbines, locomotives, financing and digital services for infrastructure, mining, energy and industrial customers through a global dealer network.
Public · 5000+ people
Source and classification
Internal deployment & tooling · Evidence for this classification:
machines to perceive their environment, make informed decisions, and support safer, more productive operations. Apply today to build the new era of construction autonomy at Caterpillar. Job Summary Own the architecture for modular perception machine learning, sensor fusion, object tracking, object persistence, and 3D mapping using perception sensor data such as camera images, lidar point clouds, 4D radar point clouds, IMU data, GNSS data, and machine state inputs. This role focuses on transforming synchronized sensor data into reliable perception outputs, including detected objects, tracked objects, persistent object representation cross machines, drivable area segmentation, and local-to-global 3D maps. These outputs must be structured for use by robotics, simulation, and safety analysis. Primary Responsibilities Define the modular perception ML architecture for camera-based
More from the job description
Career Area: Technology, Digital and Data Job Description: Your Work Shapes the World at Caterpillar Inc. When you join Caterpillar, you're joining a global team who cares not just about the work we do – but also about each other. We are the makers, problem solvers, and future world builders who are creating stronger, more sustainable communities. We don't just talk about progress and innovation here – we make it happen, with our customers, where we work and live. Together, we are building a better world, so we can all enjoy living in it. Your Work Shapes the World at Caterpillar Inc. When you join Caterpillar, you're joining a global team who cares not just about the work we do – but also about each other. We are the makers, problem solvers, and future world builders who are creating stronger, more sustainable communities. We don't just talk about progress and innovation here – we make it happen, with our customers, where we work and live. Together, we are building a better world, so we can all enjoy living in it. Help Build the Future of Caterpillar At Caterpillar, technology always has a purpose, which is to solve our customers’ toughest challenges. Through Cat Technology, we are solving problems by building the intelligence layer that connects machines, data, and people to make jobsites safer, more productive, and more sustainable. By combining deep domain expertise [... source excerpt omitted ...] esentation cross machines, drivable area segmentation, and local-to-global 3D maps. These outputs must be structured for use by robotics, simulation, and safety analysis. Primary Responsibilities Define the modular perception ML architecture for camera-based object detection and drivable area understanding, point-cloud-based ground plane segmentation and object detection, and 4D radar-aided perception. Own the sensor fusion architecture across camera, lidar, 4D radar, IMU, GNSS, and machine state data to improve perception robustness, spatial consistency, and environmental awareness. Define object tracking and object persistence architecture, including object association, object l [... source excerpt omitted ...] ld representation. Define perception output interfaces for downstream consumers, including robotics, simulation, world model creation, validation, and safety analysis. Candidate Requirements Strong experience with modular perception ML and sensor fusion for autonomous vehicles and robotics. Familiarity with construction, or off-road autonomy applications is a plus. Hands-on experience working with camera images, lidar and 4D radar point clouds, IMU, GNSS, and machine state data in real perception systems. Solid understanding of object detection, drivable area understanding, ground plane segmentation, object tracking and fusion, and 3D mapping. Ability to work cross-functionally
Employer postings · Data from · Sources