Expert AI Data Annotator & RLHF Evaluator
Text
RLHFHighly experienced AI Data Annotator and RLHF Evaluator specializing in the optimization and alignment of Large Language Models (LLMs). Core Responsibilities: - Conducted multi-turn RLHF model evaluations, ranking responses based on strict criteria for truthfulness, helpfulness, and harmlessness. - Authored adversarial prompts (red-teaming) and edge-cases to identify vulnerabilities and minimize hallucinations. - Performed high-volume, precise data annotation and quality assurance reviews to ensure superior dataset integrity. - Delivered high inter-annotator agreement rates under tight, rapidly changing project guidelines.
2021 - 2025