This is a hands-on, high-impact role where you'll make decisions on model selection, system architecture, and performance tradeoffs. Dive deep into the code and data by reading research papers, optimizing GPU training performance, debugging tricky edge cases, or reviewing videos to understand remaining failure cases. Research and develop computer vision methods for scene understanding and turn your research into robust, production-ready code.

As a research intern within the ML Perception team, you'll apply expertise to real-world multi agent autonomous driving and infrastructure challenges. You will focus on multimodal efficient deep learning for safety critical systems with built in redundancy and robustness, collaborating with a multidisciplinary team to develop innovative models and algorithms to enhance our perception stack.