AI Analyst - LLM Evaluation

: Immediate joiners or less than 30 days notice period. Support the design and evaluation of safe, grounded and useful AI learning experiences for children, including prompt behaviour, multilingual quality and model-response testing. Required Skills : - LLM prompting, evaluation methods and structured testing rubrics - Working knowledge of RAG, grounding and hallucination testing - Multilingual evaluation and dataset/test-case creation - Understanding of child-safe AI behaviour and responsible content standards - Analytical thinking, documentation and AI-cost awareness Key Responsibilities : - Define and test AI-tutor prompts, response behaviour and grounding standards - Create evaluation datasets, test cases, scoring rubrics and quality reports - Identify hallucinations, unsafe outputs and multilingual quality issues - Work with product and academic teams to improve learning accuracy - Document findings and recommend practical model or prompt improvements