Perception Intern

Mitsubishi Electric Automotive • Detroit, MI

2d

About The Position

Work closely with experienced professionals in their chosen field to apply what is learned in the classroom to real-life work situations. Under supervision, they will assist team members or directly perform day-to-day departmental functions and projects. They will gain an enhanced understanding of their field and the automotive manufacturing industry, laying the foundation for a successful career.

Requirements

• Current enrollment in a Bachelor’s, Master’s, or Ph.D. program in Computer Science, Electrical Engineering, Robotics, or a related field.
• Coursework or project-based experience in computer vision, deep learning, or robotics.
• Familiarity with at least one deep learning framework (e.g., PyTorch or TensorFlow).
• Understanding of fundamentals in data analysis, 3D geometry, and point cloud processing.
• Exposure to LiDAR data and/or related libraries (Open3D, PCL).
• Programming experience in Python.
• Ability to conduct literature surveys and summarize technical concepts accessibly.
• Strong problem-solving and communication skills, and enthusiasm for hands-on learning in a collaborative team environment.

Nice To Haves

• Familiarity with C++ is an advantage.

Responsibilities

• Research, benchmark, and test implementations of state-of-the-art deep learning models for LiDAR-based object detection and segmentation.
• Assist in improving LiDAR detection performance, particularly for complex surfaces, through literature review and experimental evaluation.
• Support the implementation and evaluation of deep learning models for LiDAR point clouds (e.g., PointNet, PointNet++, and other 3D architectures).
• Contribute to the development and assessment of perception algorithms that combine LiDAR and camera data under supervision.
• Help collect, preprocess, and analyze camera and LiDAR data for model development and testing.
• Experiment with open-source toolkits such as Open3D and PCL for point cloud processing and visualization.
• Assist in creating scripts and small pipelines for data preparation and result analysis (using Python, NumPy, OpenCV, etc.).
• Participate in code reviews, documentation, and team meetings to learn best practices in research and development.
• Stay current with recent advancements in LiDAR perception and deep learning by reading and summarizing relevant scientific papers.

What This Job Offers

• Career Level: Intern
• Education Level: Ph.D. or professional degree