AI Training Specialist (RLHF, LLM Evaluation, Annotation)
As an AI Training Specialist, I evaluated and annotated over 1,000 AI-generated text outputs across reasoning, prompt-response grading, and classification tasks. I maintained a high annotation accuracy rate exceeding 95% and applied structured feedback and RLHF workflows. I contributed significantly to model improvement through edge case identification, hallucination detection, and strict quality assurance measures. • Conducted prompt evaluation, response rating, and model alignment for LLMs. • Provided structured feedback and collaborated globally on model refinement tasks. • Used tools such as Appen, MTurk, and Internal/Proprietary Tooling for annotation. • Managed independent freelance responsibilities and maintained high-volume output.