A public company in the Automotive sector that has developed 3D systems for preventing road accidents, utilizing highly advanced technologies from image processing, computer vision, machine learning, deep learning, and more. The company is well-funded and stable, serving as a subsidiary of an established company that develops cameras used in "sensitive" locations domestically and internationally, including tunnels, airports, military installations, etc.

The company is located in the central region near a train station, and remote work is possible on

About the role-

Research and Development:

• Explore and develop models in the field of computer vision.
• Focus on processing and analyzing video and image data.

Technical Tasks:

• Perform camera calibration for precise imaging.
• Work with multi-view geometry for spatial understanding.
• Implement SLAM (Simultaneous Localization and Mapping) and SFM (Structure from Motion) techniques.
• Tackle classic computer vision tasks such as detection, segmentation, stereo vision, registration, augmentations, and motion tracking.

Coding Proficiency:

• Utilize programming languages like C++ and Python.
• Operate within an embedded environment.
• Research Responsibilities:
• Engage with state-of-the-art (SOTA) methods in computer vision.
• Review and analyze relevant articles to gain insights for improvements.
• Explore the capabilities of Deep Learning (DL) and Artificial Intelligence (AI).
• Implement optimization techniques.
• Fine-tune model parameters and other related tasks.

Technical knowledge and Qualifications:

• M.Sc. from a top university in Computer Science / Engineering / Math – Mandatory.
• At least 3 years of experience in computer vision algorithm research.
• Excellent programming skills in C/C++.
• Knowledge of Python
• Background in some of these technologies: cameras calibration / multi-view geometry / SLAM / SFM
• Great problem-solving skills and drive for innovation.