Novel AI Lead Methodologist

Job description

Drive the methodological frontier of model evaluation. Partner with DeepMind and Data Science, developing novel, data-driven methodologies for structured and unstructured testing of emerging AI products. Move beyond standard benchmarks, designing sophisticated experimental frameworks, uncovering latent model behaviors and capabilities. Define testing and safety standards, working with cross-functional colleagues to ensure they are met. Perform analyses and drive insights to develop model-level and product-level safety mitigations. Lead and influence cross-functional teams to implement safety initiatives. Advise executive leadership on complex safety issues. Represent Google's AI safety efforts in external forums and collaborations, contributing to industry-wide best practices. Mentor analysts, fostering a culture of excellence, acting as a subject matter expert on adversarial techniques. Work with sensitive content or situations and may be exposed to graphic, controversial or upsetting topics or content.