Milwaukee, Wisconsin30+ days ago
Experience with agent patterns and tooling (e.g., tool/function calling concepts, orchestration, RAG/grounding, and basic evaluation approaches), including MCP (Model Context Protocol) features for linking models to tools and data sources. Test and evaluate AI outputs for accuracy, usefulness, consistency, and policy alignment; build lightweight test sets, capture failure modes, and recommend improvements to prompts, grounding, and workflow/agent design.