O

Origin

AI-powered robot automating interior finishing trades

Perception Engineer Apprentice

InternshipUpdated
₹600k - ₹720k
Bengaluru, Karnataka, India
In Person
AI & Machine LearningComputer Vision

About the job

Requirements
  • A solid grasp of linear algebra, probability, and geometry, with coursework or projects in computer vision or robotics perception.
  • Proficiency in Python 3.x and C++17/20, and comfort with Git and continuous-integration workflows.
  • Experience with ROS 2, including rclcpp/rclpy and custom message and launch setups.
  • Familiarity with deep-learning vision using PyTorch or TensorFlow, including classification, detection, or segmentation.
  • Hands-on experience with point-cloud processing using PCL or Open3D, including voxel grids, KD-trees, RANSAC, or ICP.
Responsibilities
  • Build ROS 2 nodes for 3-D point-cloud ingestion, filtering, voxelisation, and wall-plane extraction using PCL or Open3D.
  • Train and integrate CNN or Transformer models for surface-defect detection and semantic segmentation.
  • Implement RANSAC-based pose, plane, and key-point estimation, refined with ICP or Kalman/EKF loops.
  • Fuse LiDAR, depth-camera, IMU, and wheel-odometry data for robust SLAM and obstacle avoidance.
  • Optimize and benchmark models on Jetson-class edge devices with TensorRT or ONNX Runtime.
  • Collect, label, and augment real and synthetic datasets, and automate experiment tracking using Weights & Biases or MLflow.
  • Collaborate with manipulation, navigation, and cloud teams to ship production-ready perception stacks.
Desired Qualifications
  • Exposure to camera–LiDAR calibration or real-time optimization libraries such as Ceres or GTSAM.

About the company

Origin builds a general-purpose construction robot that automates interior finishing trades such as drywall finishing and painting on real job sites. The AI-powered system can operate power tools and work alongside human crews across multiple trades. It is already deployed on live job sites in New York City with major contractor partners. Its goal is to enable scalable, high-quality, and cost-efficient construction by augmenting or replacing manual interior finishing work with intelligent robotics.

Company Size

N/A

Company Stage

Early VC

Total Funding

$20M

Headquarters

N/A

Founded

2025

Get referred to Origin

See people who can refer or advise you

Simplify Jobs

Simplify's Take

What believers are saying

  • March 2026 caps reached multiple global beverage brands, showing real customer validation.
  • February 2026 Matrix partnership extends 2026 qualification trials and product runs.
  • September 2025 Starlinger equipment financing supports PET sheet production through 2029 repayment.

What critics are saying

  • Origin approved dissolution on August 12, 2026, making employer durability existentially weak.
  • Management cut 59% of staff on May 1, 2026, and John Bissell stepped down.
  • Cash lasts only into Q3 2026 without financing, forcing asset sales or shutdown.

What makes Origin unique

  • Origin still owns PET cap technology with customer-requested designs and qualification data.
  • Matrix Bottling partnership broadens commercialization through U.S. bottling and capping services.
  • HP Embalagens distribution gives Origin access to Nestlé, Ferrero Rocher, and J&J networks.

Help us improve and share your feedback! Did you find this helpful?

Company News

Mint
Oct 15th, 2026
Origin raises $20 million from Accel, Zacua to scale construction robotics in the US, Europe | Company Business News

The deeptech startup plans to deploy 150 autonomous robots by next year on a subscription model, offering Western contractors up to 20% savings amid severe labour shortages.