Perception Intern
Core
Develop 2D image and 3D point cloud models for object and panoptic detection of urban and roadway features like traffic lights, utility poles, curbs, and painted road markings.
Role type
Intern, perception engineer (computer vision)
Builds
Real-time detection models for edge mapping hardware systems
Domain
Geospatial technology, autonomous driving infrastructure
Deliverable
production ML models
Required skills
Python, algorithmic problem-solving, heuristic/geometry-based algorithms, machine learning frameworks (PyTorch, Jax), computer vision
Preferred skills
Geospatial data analysis, clean code design, independent work on complex tasks
Technologies
PyTorch, Jax
Responsibilities
Develop prototypes for detecting paint lines and curbs; optimize perception models for real-time performance on edge hardware; tune machine learning models for accuracy and performance
Seniority
Intern