2027 Summer Intern, Perception - Evaluation

Responsibilities

• Improve signal quality in large-scale perception evaluation workflows using generative AI, including LLMs and VLMs.
• Expand the discovery evaluation system to cover additional perception signals.
• Design and develop frameworks and methods for evaluating multitask perception models.
• Collaborate with ML and infrastructure engineers to integrate new signals into end-to-end model launch evaluation.
• Evaluate improvements in evaluation quality, focusing on precision, recall, and reliability.

Requirements

• Be enrolled in a master’s or PhD program in Computer Science, Robotics, or a similar technical field.
• Have proficiency coding in Python or C++ and navigating large codebases.
• Have experience building and/or evaluating machine learning models.
• Have experience with data analysis and statistical evaluation.
• Preferred: multi-year C++ experience with contributions to large codebases or open-source projects.
• Preferred: familiarity with perception models, especially object generation and semantic tasks.
• Preferred: experience using AI-powered workflows for data analysis or model evaluation.
• Preferred: experience applying machine learning concepts and evaluation methodologies.
• Preferred: experience building data and evaluation pipelines and processing large-scale datasets.

Benefits

• Eligible interns may participate in the company’s benefits programs, subject to eligibility requirements.
• Hybrid/on-site internship based at Waymo’s headquarters in Mountain View, California.
• Applications are accepted on a rolling basis until the role is filled.