AI Training & Evaluation Specialist (Remote)
Developed prompts, rubrics, and training tasks for large language models to support multi-source research workflows and realistic user scenarios. Built evaluation frameworks for product-research and synthesis tasks involving cross-source validation, tradeoff analysis, and structured reasoning. Served as both contributor and early reviewer by auditing submissions and reinforcing quality standards through live and asynchronous feedback. • Prompt and rubric authoring for LLM training • Evaluation framework design for research/synthesis • Reviewer audits with targeted feedback and onboarding support • Live review collaboration with rapid guideline updates