Perception Engineer

About this role

About Origin
Origin (previously 10xConstruction) is building general-purpose autonomous robots for US construction to tackle rising costs, safety risks, and labor shortages. Our modular, multi-trade platform combines purpose-built hardware with real-time site intelligence to navigate complex environments and execute tasks with precision. Trained in high-fidelity simulation and already deployed on live sites, our robots deliver 5x faster execution, 250%+ margin expansion, and significant cost savings. Join India’s most talent-dense robotics team consisting of individuals from IITs, Stanford, UCLA, etc.

About the Role
As a Perception Engineer at Origin (Formerly 10xconstruction), you will help our autonomous drywall-finishing robots "see" the job-site. You'll design and deploy perception pipelines—camera + LiDAR fusion, deep-learning vision models, and point-cloud geometry—to give the robot the awareness it needs.

Key Responsibilities

• Develop and deploy 3D perception components for geometric scene understanding using depth sensors, LiDAR, and RGB cameras.

• Build ROS 2 nodes that process and interpret spatial data (point clouds, depth maps, image streams) for environment modeling and task planning.

• Train and integrate deep-learning models for 3D semantic understanding, including surface analysis and object segmentation.

• Design robust sensor fusion strategies that combine visual, inertial, and spatial data for scene reconstruction and robot localization.

• Benchmark and optimize perception models for deployment on edge compute platforms (e.g., NVIDIA Jetson) using tools like TensorRT or ONNX.

• Collect and curate high-quality datasets (real and synthetic); automate training pipelines and experiment tracking.

• Collaborate across robotics teams (manipulation, navigation, cloud) to deliver production-ready perception stacks for autonomous operation in dynamic construction environments.
Requirements
Qualifications & Skills

• Solid grasp of linear algebra, probability and geometry; coursework or projects in CV or robotics perception.

• Proficient in Python 3.x and C++17/20; comfortable with git and CI workflows.

• Experience with ROS 2 (rclcpp / rclpy) and custom message / launch setups.

• Familiarity with deep-learning vision (PyTorch or TensorFlow)—classification, detection or segmentation.

• Hands-on work with point-cloud processing (PCL, Open3D); know when to apply voxel grids, KD-trees, RANSAC or ICP.

• Bonus: exposure to camera–LiDAR calibration, or real-time optimization libraries (Ceres, GTSAM).

Good to have:

• Python 3.x

• C++17/20

• ROS 2

• PyTorch

• Open3D

• RANSAC