Financial Markets Specialist & AI Logic Evaluator (LLM auditing/training focus).
Text
RLHFTransitioned financial risk expertise into evaluating, auditing, and training Large Language Models (LLMs) with strict mathematical precision requirements. Focused on safety/protocol-aligned evaluation and edge-case testing tied to risk and compliance logic. Worked as an AI logic evaluator to ensure model behavior matches financial constraints and risk calculation correctness. • Evaluated LLM outputs against financial logic, risk calculations, and compliance constraints. • Audited mathematical consistency and resolved discrepancies between expected accounting logic and dynamic evaluation. • Performed edge-case testing to validate robustness of model reasoning under risk-related scenarios. • Supported RLHF-style evaluation through rating and feedback aligned with financial safety and correctness criteria.