Lead AI Content Evaluator & Trainer
I conducted high-complexity RLHF tasks and creative writing evaluations for AI content models. My responsibilities included identifying bias, vulnerabilities, and harmful outputs through red teaming and evaluating AI-generated code, math, and narratives for accuracy. The role involved continual collaboration to improve AI models and prevent undesirable behaviors. • Managed RLHF and red team evaluation tasks for diverse AI-produced content. • Assessed text, computer code, and narratives for quality and safety. • Provided detailed feedback to enhance LLM behavior alignment. • Ensured deadlines were met while working remotely in a fast-paced environment.