Lead Perception Engineer

Origin; Bengaluru; On-site; INR 334,800 - 558,000; Full time

Job summary

A robotics company in Bengaluru is looking for a final year or pre-final year B.Tech or M.Tech student to develop and optimize 3D perception systems for autonomous robots. The ideal candidate should have a strong foundation in computer vision, be proficient in Python, and be familiar with machine learning frameworks like PyTorch or TensorFlow. Candidates will work closely with collaborative teams, focusing on real-time performance and robust perception in complex environments. This is a unique opportunity to be part of an innovative robotics team.

Qualifications

• Final year or pre-final year student in relevant field.
• Strong fundamentals in computer vision and 3D perception.
• Proficiency in Python; C++ is a plus.

Responsibilities

• Develop and deploy 3D perception components using LiDAR and depth sensors.
• Train and integrate deep learning models for 3D semantic understanding.
• Design and implement sensor fusion strategies.

Skills

Computer vision fundamentals

3D perception

Python programming

Familiarity with machine learning frameworks

Education

B.Tech or M.Tech in Robotics, Computer Science, Electronics

Tools

PyTorch

TensorFlow

OpenCV

Job description

Overview

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