Desay SV, one of the leading mobility technology companies, is committed to be the preferred partner in mobility transformation. Desay SV’s core business focuses on the efficient integration of the three major areas of smart cabin, smart drive, and smart service. We continue to develop highly integrated leading hardware and software algorithms to provide global customers with safe, comfortable, and efficient mobility solutions and services.

Project Background:

With the rapid expansion of autonomous driving technologies, our company is dedicated to pioneering advanced computer vision and machine learning solutions. We focus on critical areas such as semantic mapping, change detection, and localization to support robust and reliable autonomous systems. By collaborating with industry experts, academic researchers, and cross-functional teams, we continually push the boundaries of AI-driven solutions that can handle large-scale, real-world challenges. This internship offers the chance to contribute directly to the Localization and Mapping team, where you will help develop next-generation solutions that shape the future of autonomous mobility.

Scope:

Our Localization and Mapping team consists of diverse group of engineers, researchers, and data scientists who specialize in designing production-scale CV/ML systems for autonomous driving. The team’s responsibilities range from developing next-generation mapping solutions to ensuring robust calibration and localization across various platforms. By joining us, you will:

• Work alongside experts in computer vision, machine learning, and robotics.
• Contribute to real-world projects that have a direct impact on the future of autonomous mobility.
• Gain hands-on experience in both the research and engineering aspects of AI-driven perception, mapping, and calibration.

Job Tasks:

1. Contribute to Semantic Mapping Solutions

• Assist in designing and implementing automated semantic mapping pipelines.
• Work with point cloud, image, and other sensor data using state-of-the-art CV/ML techniques.

2. Data Processing and Model Integration

• Collaborate with senior team members to preprocess and analyze large datasets (point clouds, images, etc.).
• Help integrate machine learning models (e.g., segmentation, object detection) into existing pipelines.

3. Software Development and Deployment

• Write efficient and scalable code (C++ or Python) for cloud-based and on-premise systems.
• Participate in code reviews, testing, and documentation to ensure high-quality software.

4. Research and Innovation

• Stay updated on the latest advancements in computer vision and machine learning.
• Propose improvements or new techniques to enhance the accuracy, speed, or robustness of our systems.

Requirements:

• Bachelor or Master Degree in Computer Engineering, Computer Science, Electrical Engineering, Robotics or related field. 
• Fundamental knowledge of computer vision and/or machine learning techniques (e.g., SLAM, point cloud processing, scene reconstruction).
• Proficiency in C++ or Python with solid understanding of software engineering principles (source control, testing, code reviews).
• Exposure to frameworks like PyTorch, TensorFlow, OpenCV, or related libraries is a plus.

• Self-motivated and eager to learn new technologies, tools, and approaches in AI and autonomous systems.