Agentic AI Evaluation Scientist - Responsible AI & MLOps
Summary
Designs and runs evaluation frameworks for conversational and autonomous AI agents in commerce, embedding tests into MLOps and CI/CD to measure task completion, tool-use, bias, and customer experience.
Cognizant is seeking an experienced Agentic AI Evaluation Data Scientist to design and implement evaluation frameworks for conversational and autonomous AI in commerce. You will assess agent performance across task completion, tool-use accuracy, bias, and customer experience, building automated pipelines and embedding evaluation gates into MLOps and CI/CD.
You will collaborate with AI Engineers and Solution Architects, implement red-teaming and regression testing, and communicate risk to