Practical AI Experience (Required): Proven track record of successfully implementing, shipping, and scaling production-grade applications leveraging Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and AI agentic frameworks (e.g., MCP). This includes hands-on experience establishing evaluation, testing, and observability guardrails using modern LLM tooling (such as LangSmith, Phoenix, Braintrust, Langfuse, or Arize).