AI Trainer / Code Evaluator (part-time/project-based availability includes LLM output review, technical QA, and RLHF feedback)
Provided AI training and evaluation support focused on LLM code assessment and correctness review. Applied STEM-domain expertise to judge technical reasoning, factuality, and safety in model outputs. Delivered structured feedback suitable for iterative model improvement and QA workflows. • Reviewed and evaluated generated code for correctness • Performed LLM output evaluation including factuality and reasoning • Conducted technical content accuracy checks • Supported RLHF-style preference feedback and iteration