Business Analyst

Evaluate AI outputs (voice-to-text transcripts, chat, email, summaries) for adherence to banking QA standards and LLM metrics. **Key Responsibilities:** - Rate and annotate AI responses based on custom metrics (accuracy, empathy, tone). - Compare LLM outputs vs gold-standard responses. - Support fine-tuning dataset creation for Cekura. - Validate hallucinations, factual accuracy, and compliance alignment. **Required Skills:** - Understanding of LLM evaluation principles. - Strong English + Hindi proficiency (multi-lingual is a plus). - Familiarity with annotation tools and basic Python for data parsing. **Preferred:** - Exposure to BFSI datasets or regulatory QA work.