AI Model Training & Evaluation Specialist
Contributed to the training and evaluation of large language models in reinforcement learning from human feedback pipelines. Performed qualitative and compliance-focused annotation of model responses for accuracy, safety, and policy alignment. Supported large-scale, high-throughput annotation environments using structured workflows and detailed scoring rubrics. Maintained quality and consistency across thousands of model evaluations. • Evaluated and ranked model outputs for instruction adherence, conversational quality, and safety • Identified hallucinations, logical inconsistencies, and provided structured feedback • Annotated and reviewed responses under strict policy and quality guidelines • Participated in instruction tuning and preference ranking tasks relevant to LLMs.