LLM Trainer/Evaluator (Finance Domain)
Trained and evaluated LLM-based financial analysis systems, focusing on improving AI understanding of corporate finance and valuation. Created structured prompts and multi-step reasoning frameworks for financial tasks and scenario-based business problems. Designed, reviewed, and optimized finance-specific datasets, enhancing the reliability and logical consistency of AI outputs. • Developed datasets to improve instruction following in financial modeling and reporting • Refined evaluation criteria and prompts for financial analytical tasks • Validated and optimized AI-generated financial insights for accuracy • Collaborated on prompt engineering and evaluation in a finance domain context