Computer Vision Researcher – Advanced Robotics

As a Computer Vision Researcher, You will be responsible for designing and optimizing deep learning models, building prototypes, and collaborating closely with cross-functional teams to ensure seamless integration and real-time deployment of computer vision technologies into robotic systems. Be a part of our ambitious Advanced Robotics team, which is dedicated to pushing the boundaries of robotics and launching new products.

The role of Computer Vision Researcher role is based out of Noida Headquarters. In this role, you will play a crucial role in developing a robot vision system that will enable humanoid robots to navigate, interact, and learn from complex and dynamic environments. You would design and implement software algorithms for perception, localization, mapping, and navigation tasks.

  • Noida

Responsibilities

  • Conduct advanced research in computer vision, including areas such as image segmentation, object detection, motion tracking, sensor fusion, etc to develop efficient algorithms that enable robots to identify objects, navigate complex environments, and interact with their surroundings accurately in real-time 
  • Design, train, and optimize deep learning models (e.g., CNNs, RNNs, GANs) for computer vision tasks. Work with large datasets to train and fine-tune models for improved accuracy and performance.
  • Implement efficient data processing pipelines for handling large-scale datasets. Utilize data augmentation techniques to improve the robustness of models. 
  • Build prototypes and proof-of-concept systems that integrate computer vision algorithms into practical applications. Develop software solutions that translate research findings into usable products. 
  • Evaluate and optimize the performance of computer vision models for real-time applications. Work on optimizing models for both accuracy and computational efficiency, particularly for deployment on embedded or mobile devices. 
  • Facilitate the integration of third-party computer vision libraries and frameworks into the robotic control stack, ensuring smooth operation and compatibility with existing systems.   
  • Collaborate with product teams, hardware engineers, and software developers to integrate computer vision technologies with hardware to develop robot movements and features.
  • Mentor junior researchers and engineers on computer vision concepts and technologies. Provide guidance in experimental design, data analysis, and the development of algorithms. 

Key Skills, Qualifications, and Required Years of Experience

  • PhD or master's degree in computer science, Computer Vision, AI, Robotics, or a related field 
  • 5-8 Years of Experience
  • Strong understanding of computer vision techniques including image processing, feature extraction, object detection, segmentation, and tracking. 
  • Proficiency in deep learning frameworks such as TensorFlow, PyTorch, Keras, or Caffe. 
  • Experience with Visual SLAM; LiDAR SLAM and VIO is recommended.  
  • Hands-on experience with convolutional neural networks (CNNs), recurrent neural networks (RNNs), and generative adversarial networks (GANs). 
  • Some knowledge of Visual Language Action (VLA) is recommended.  
  • Familiarity with traditional computer vision techniques (e.g., SIFT, SURF, HOG, Optical Flow). 
  • Solid programming skills in  C++, Python or other relevant languages. 
  • Experience with data processing, augmentation, and handling large image datasets (e.g., COCO, ImageNet). 
  • Experience with computer vision libraries such as OpenCV, or scikit-image. 
  • Familiarity with GPU programming (CUDA) for training deep learning models on large datasets. 
  • Strong foundation in machine learning algorithms and statistical methods. 
  • Experience in model evaluation metrics, performance analysis, and optimization techniques. 
  • Ability to stay current with the latest research trends in computer vision and apply cutting-edge methods to solve practical problems.
 

Apply now