Senior Prompt Engineer

A practical toolkit for the actual work of prompt engineering: optimizing token usage, evaluating RAG pipelines, and validating agent configurations. The prompt optimizer analyzes clarity and cost, surfaces redundancies, and suggests structural improvements. The RAG evaluator measures context relevance and answer faithfulness with specific metrics. The agent orchestrator visualizes workflows and catches configuration issues before runtime. This is less about theory and more about the repetitive debugging work that comes up when you're tuning prompts for production, tracking down why retrieval quality dropped, or figuring out if your agent is going to loop forever. Solid for anyone who spends time staring at LLM outputs wondering why they're inconsistent.