2027 Summer Intern, MS/PhD, Perception, Evaluation

Tech Stack

Responsibilities

• Improve signal quality in large scale perception evaluation workflows using generative AI (LLM/VLM)
• Expand the capabilities of discovery evaluation system to cover a broader range of perception signals
• Contribute to design and development of frameworks and methods for evaluating multi-task perception models
• Collaborate with ML and infra engineers to integrate new signals to end-to-end model launch evaluation
• Evaluate the impact of improvements on evaluation quality, focusing on precision, recall, and reliability

Culture

Requirements