Technical AI Evaluator
As a Technical AI Evaluator, I participated in evaluating AI-generated code to improve its correctness and security. My work involved providing expert-level feedback on model outputs as part of reinforcement learning from human feedback (RLHF) processes. The evaluation covered multiple programming languages and frameworks, with a focus on safe and accurate code generation. • Assessed logic, security, and efficiency of AI-generated code outputs. • Provided guided annotations and corrections for training AI coding models. • Focused on Rust and Solidity code within web and blockchain ecosystems. • Contributed to improving model accuracy for secure smart contract generation.