AI Prompt Engineer & Evaluator (Independent) | Superteam Nigeria / Solana Ecosystem
Evaluated AI/LLM outputs for logical consistency, factual accuracy, and instruction adherence across development workflows. Produced structured feedback aligned with RLHF-style preference evaluation and rating criteria. Applied prompt engineering to drive accurate generation and reliable structured outputs. • Rated responses for accuracy, helpfulness, safety, and instruction-following • Identified ambiguity, hallucinations, and factual errors in model outputs • Performed RLHF-style preference ranking and generated structured feedback • Tested and iterated prompts for coding, reasoning, and general knowledge domains