
Professional with experience in high-volume annotation and evaluation of LLM-generated responses, focusing on summarization, recasting, and taxonomy classification. Demonstrated ability to participate in scoring projects utilizing Faithfulness, Helpfulness, and Fluency metrics under established guidelines. Skilled in conducting similarity evaluations between incidents and knowledge base articles while generating structured relevance-based comments. Proven track record of identifying linguistic ambiguities and ensuring compliance with guidelines through peer-level feedback and process refinement contributions.
Performed high-volume annotation and evaluation on tasks involving LLM-generated responses, summarization, recasting, and taxonomy classification.
● Participated in scoring projects using Faithfulness, Helpfulness, and Fluency metrics under CCG guidelines.
● Handled similarity evaluation between incidents and knowledge base (KB) articles; generated structured relevance-based comments.
● Identified linguistic ambiguity and ensured guideline-compliant output.
● Provided peer-level feedback and raised edge cases to Content Leads, contributing to process refinement.
Best performer awards in multiple quarters in the Labelling tenure.
Consistent positive feedback from CLs for review quality and ownership.