Senior Perception Engineer

Description

About Origin-
Origin (previously 10xConstruction) is building general-purpose autonomous robots for US construction to tackle rising costs, safety risks, and labour 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-
You will work on building and optimizing 3D perception systems that enable robots to understand and interact with complex real-world environments. The goal is to develop robust perception pipelines that work reliably across both simulation and real-world construction sites, ensuring accurate scene understanding, localization, and decision-making.

Key Responsibilities-

3D Perception Development

• Develop and deploy 3D perception components using LiDAR, depth sensors, and RGB cameras
• Process and interpret spatial data such as point clouds, depth maps, and image streams
• Build pipelines for environment modeling and task planning
  

Deep Learning & Scene Understanding

• Train and integrate deep learning models for 3D semantic understanding
• Work on object detection, segmentation, and surface analysis in 3D environments
• Improve robustness of perception models in dynamic, real-world conditions

Sensor Fusion & Localization

• Design and implement sensor fusion strategies combining visual, inertial, and spatial data
• Contribute to scene reconstruction and robot localization systems

Optimization & Deployment

• Benchmark and optimize perception models for edge devices (e.g., NVIDIA Jetson)
• Use tools like TensorRT and ONNX for efficient deployment
• Ensure real-time performance in resource-constrained environments
  

Data & Experimentation

• Collect, curate, and manage datasets (real and synthetic)
• Build and maintain training pipelines and experiment tracking systems
  

Evaluation & Calibration

• Develop online/offline sensor calibration strategies
• Define qualitative and quantitative metrics for perception performance
• Track model performance and regression across iterations
  

Collaboration

• Work closely with navigation, manipulation, and cloud teams
• Contribute to building production-ready perception stacks for autonomous robots

Requirements

• Final year / pre-final year B.Tech or M.Tech in Robotics, Computer Science, Electronics, or related field
• Strong fundamentals in computer vision and 3D perception
• Proficiency in Python (C++ is a plus)
• Familiarity with PyTorch / TensorFlow
• Basic understanding of point clouds, SLAM, or sensor fusion
• Ability to work with real-world data and debug complex systems

Nice to Have

• Experience with ROS/ROS2
• Hands-on experience with LiDAR, RGB-D cameras, or IMUs
• Familiarity with OpenCV, PCL, or similar libraries
• Exposure to TensorRT or ONNX
• Experience working on robotics or vision-based projects