Perception Engineer - Apprentice
At a glance
Mid-level AI Research role at Origin. Bengaluru · full-time.
Pay not stated AI Research salary
aimlroles summary, based on the employer's posting.
What you'll do
- Build 3D perception components that interpret depth, LiDAR and camera inputs to map surrounding geometry
- Turn point clouds, depth maps and image streams into environment models that support task planning
- Train and integrate vision models for 3D scene meaning and quality assessment
- Fuse visual, inertial and spatial signals, then calibrate sensors and check calibration quality over time
- Prepare datasets and training experiments, then benchmark and optimize models for edge deployment
What you bring
- You have coursework or project work in computer vision or robotics perception, with grounding in geometry, probability and linear algebra
- You can develop in Python and C++, and have used Git, CI workflows and ROS 2
- You have worked with deep-learning vision and point-cloud processing, including methods such as voxel grids or ICP
- You have some exposure to sensor-calibration algorithms
Who this fits
This suits an early-career perception engineer who wants hands-on work across 3D vision, sensor fusion and robot deployment. The role is based onsite in Bengaluru.
From the employer
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.
- 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 and quality evaluation.
- 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.
- Perform and validate sensor calibration (camera, LiDAR, IMU) and develop checks to maintain calibration quality over time
- 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 ; know when to apply voxel grids, KD-trees, RANSAC or ICP.
- Exposure to sensor calibration algorithms,
Good to have:
- Experience with ROS 2
- Familiarity with PCL, Open3D
- Exposure to real-time optimization libraries (Ceres, GTSAM).