Position Overview
We are looking for interns to join our team and assist on cutting-edge projects in perception, data mining, and 3D reconstruction. Gain hands‑on experience with multi‑modal datasets, vision‑language models (VLM), generative AI, and world models for synthetic data generation.
Key Responsibilities - Assist in collecting and organizing multi‑modal datasets for AI perception projects.
- Support automated data mining using vision‑language models (VLM) and help generate synthetic training data with world models.
- Help benchmark and evaluate AI models, and assist with camera calibration and post‑processing.
- Contribute to semantic 3D reconstruction experiments, preparing data and analyzing results.
- Work closely with engineers and researchers to support model integration and validation in real‑world scenarios.
Qualifications & Experience - Current undergraduate or master’s student in AI, Robotics, Computer V...