As a member of this team, you will be at the forefront of Google Search, pioneering the evaluation of groundbreaking AI products. We provide the essential groundwork for Search’s primary Generative AI products, including AI overview and AI mode. By developing SOTA AI Raters and advanced measurement frameworks, we try to ensure high quality for AI-generated responses. We work on the most complex challenges in AI quality, architecting novel ways for billions of users to experience Google’s capabilities on a daily basis. This is a unique opportunity to shape and refine the future of state-of-the-art Search AI products at Google.
In this role, you will evaluate and improve the Google Search user experience. We work on challenging problems at the frontiers of Generative AI evaluation, and collaborate cross-functionally. We use available data sources (human ratings, offline eval, live experiments, user surveys, etc.) to bring analytical accuracy and statistical methods to the challenges of measuring quality, developing metrics, and improving training data for model development.
As a key member of the team, you work with engineers and researchers to analyze/interpret data, develop metrics, and integrate new methodologies into existing evaluation systems.
Individual pay is determined by factors including job-related skills, experience, and relevant education or training.
US: $174000 - $253000 (USD) + 15% bonus target + equity + benefits
Learn more about benefits at Google.
Responsibilities
- Work with large, complex data set and solve difficult, non-routine analysis problems, applying advanced analytical methods as needed. Conduct end-to-end analysis that includes data gathering and requirements specification, processing, analysis, ongoing deliverables, and presentations.
- Build and prototype analysis pipelines iteratively to provide insights at scale. Develop comprehensive understanding of Google data structures and metrics, advocating for changes where needed for both products development and business strategy.
- Interact cross-functionally with a wide variety of people and teams. Work closely with engineers to identify opportunities for design, and assess improvements to Google products.
- Make business recommendations (e.g., cost-benefit, forecasting, experiment analysis) with effective presentations of findings at multiple levels of stakeholders through visual displays of quantitative information.
- Research and develop analysis methods to improve the quality of Google Search.
Qualifications
Minimum qualifications:
- Master's degree in Statistics, Data Science, Mathematics, Physics, Economics, Operations Research, Engineering, or a related quantitative field.
- 5 years of work experience using analytics to solve product or business problems, coding (e.g., Python, R, SQL), querying databases or statistical analysis, or 3 years of work experience with a PhD degree.
Preferred qualifications:
- 8 years of work experience using analytics to solve product or business problems, coding (e.g., Python, R, SQL), querying databases or statistical analysis, or 6 years of work experience with a PhD degree.
- Experience working with eval data (human and AI rated).
- Strong organization, prioritization, written and verbal communication skills.