Computer Vision Engineer
Location
Mumbai
Job Overview
Join our cutting-edge Robotics team as a Computer Vision Engineer, where your primary role will involve researching, designing, developing, deploying, and maintaining advanced computer vision applications. These applications are vital for the autonomy and efficiency of our robots, enhancing their perception and operational capabilities in environments. You will work closely with deep learning algorithms and image classification to integrate and interpret data from point clouds, playing a pivotal role in improving the robots' interaction with their surroundings.
What you will be doing:
Develop and refine computer vision algorithms that enhance the robot's perception using OpenCV, Point Cloud Library, and other relevant technologies.
Implement and maintain systems for object detection, tracking, and 3D geometry.
Contribute to the calibration of cameras, understanding of epipolar geometry, matching feature points, and edge detection.
Apply deep learning frameworks (e.g., TensorFlow, PyTorch) for image and data analysis tasks.
Engage in continuous learning to apply the latest research findings in computer vision to practical applications.
Write efficient, reliable Python, C/C++ code and optimise existing algorithms for performance improvements.
Work with Point Cloud data and utilise the PCL library effectively.
Develop, test, and deploy machine learning models, ensuring the reliability and efficiency of ML servers on AWS.
Collaborate with the dataset team to obtain and preprocess data for model training.
Design and implement deployment scripts for seamless integration and scalability of models.
Monitor and maintain the performance of online machine learning servers, ensuring high availability and reliability.
What we hope to see in you:
2+ years of relevant experience in computer vision engineering or a related field.
Proficiency in computer vision frameworks such as OpenCV and deep understanding of CV tasks.
Strong foundation in linear algebra, multi-view geometry, and numerical optimization.
Excellent programming skills in Python, C/C++, with a focus on clean code, strong engineering practices, and multi-threaded programming.
Experience with Point Cloud data and familiarity with the PCL library.
Working knowledge of deep learning frameworks (TensorFlow, PyTorch, etc.).
Keen ability to stay updated with and implement the latest computer vision research findings.
Experience with GPU programming (CUDA/OpenCL) and OpenGL is advantageous.
Bachelor’s degree in Computer Science or a closely related field is required.
All candidates must have atleast a Bachelor’s degree in Computer Science or a related field.