Cresta 3 часа назад

AI Agent Evaluation Engineer

  • Remote
  • Удалённо
PythonLLMRegression TestingEvaluationTechnical WritingcalibrationMultilingualannotationconversation analysisGolden Setsrubric designsampling

Описание

Responsibilities

  • Define quality rubrics for AI agents
  • Analyze production conversations
  • Build automated evaluation systems such as LLM judges, golden sets and regression suites calibrated against human judgment