Math Expert
Utilise Reinforcement Learning from Human Feedback (RLHF) to help machine learning models learn more efficiently - Ensure models adhere to legal and ethical obligations (i.e., harmlessness, truthfulness, safety, etc.) - Prompt engineering with various parameters and producing assessments of results Quality Assurance for other analysts’ work (prompts, feedback, conversations, instruction-following, etc.) - Process supervision, multimodal training - Supervised Fine-Tuning (SFT) for next-generation large language models (LLMs). - Collaborate with AI researchers and data scientists to train and evaluate large language models (LLMs) on complex mathematical reasoning and problem-solving tasks. - Review, verify, and annotate mathematical content ranging from basic arithmetic to advanced topics such as calculus, linear algebra, probability, and statistics. - Provide high-quality solutions and step-by-step explanations to ensure model accuracy and conceptual understanding. - Analyse AI-gener