I’m Carles Rodríguez, a Senior Quality Engineer focused on AI systems—especially LLM evaluation and quality assurance for chat, search, and RAG workflows. I’ve built and applied reliable LLM-as-a-Judge evaluation frameworks, including gold standards, rubrics, and scoring criteria designed for repeatability and consistent decision-making across distributed teams. I’ve worked on hallucination detection, retrieval grounding validation, instruction-following checks, and multilingual quality review (Spanish/Catalan/English). I enjoy turning evaluation findings into actionable improvements—through calibration, inter-rater consistency work, structured QA procedures, and detailed failure-mode analysis—while supporting AI alignment and safety quality in real-world production pipelines.…I’m Carles Rodríguez, a Senior Quality Engineer focused on AI systems—especially LLM evaluation and quality assurance for chat, search, and RAG workflows. I’ve built and applied reliable LLM-as-a-Judge evaluation frameworks, including gold standards, rubrics, and scoring criteria designed for repeatability and consistent decision-making across distributed teams. I’ve worked on hallucination detection, retrieval grounding validation, instruction-following checks, and multilingual quality review (Spanish/Catalan/English). I enjoy turning evaluation findings into actionable improvements—through calibration, inter-rater consistency work, structured QA procedures, and detailed failure-mode analysis—while supporting AI alignment and safety quality in real-world production pipelines.WWWW…