Computer Vision Engineeer

Role Overview

We are looking for a Computer Vision Engineer to develop and optimize perception, scene understanding, mapping, and multi-sensor fusion systems for advanced robotic platforms operating in complex, unstructured, and GPS-denied environments.

Key Responsibilities

Required Technical Skills

Qualifications

Strong debugging and system integration capabilities.

Experience developing real-time perception and sensor-fusion systems.

Master’s or PhD in Computer Vision, Robotics, AI/ML, Computer Science, or related fields.

Simulation tools such as Gazebo, CARLA, or Isaac Sim.

Docker, cross-compilation, and embedded deployment.

Linux, multithreading, and real-time processing.

NVIDIA Jetson AGX Orin, CUDA, and Numba-JIT optimization.

ROS 2, TF, message passing, and distributed robotics systems.

Probabilistic methods, state estimation, and uncertainty handling.

Sensor calibration, synchronization, and data alignment.

Multi-sensor fusion involving Camera, LiDAR, Radar, IMU, and GPS.

Perception algorithms, scene understanding, and environment representation.

Computer Vision, Image Processing, Object Detection, and Object Tracking.

Strong programming proficiency in C++ (14/17/20) and Python.

Debug perception-related issues, including calibration drift, synchronization, and sensor-data inconsistencies.

Conduct field testing, data collection, performance evaluation, and algorithm improvements.

Optimize perception algorithms for real-time execution on embedded computing platforms.

Develop robust perception systems capable of handling uncertainty, sensor dropouts, and changing environmental conditions.

Handle sensor calibration, synchronization, data alignment, and noise reduction.

Develop multi-sensor fusion pipelines integrating camera, LiDAR, radar, IMU, and GPS data.

Build environment mapping and world modelling systems using camera, LiDAR, and other sensor inputs.

Develop dynamic scene understanding, object tracking, and multi-entity state estimation pipelines.

Design and implement computer vision and perception algorithms for robotic systems.