Execute quality iterations on reference agents identifying potential model or agent framework improvements. Source or facilitate creation of datasets for evaluation and training to improve model performance for Cloud customers. Design new agentic systems and context engineering algorithms, utilizing existing models and identifying the need for new training/evaluation objectives where necessary. Define and implement metrics that correspond to business problems. Prototype and iterate on the solution working closely with customers, product management and business development.
Job description provided by Google.
View the original posting