Leads open-source ML research by designing experiments, developing evaluation methodologies, analyzing preference data, and releasing datasets/code to advance AI model transparency. Requires PhD-level expertise in ML/LLMs and hands-on experience with RLHF/DPO fine-tuning.
Designs and conducts experiments to evaluate AI models using human preference data, develops new metrics and methodologies, and analyzes large-scale interaction data to advance model reliability and alignment.
Leads open-source ML research by designing experiments, developing evaluation methodologies, analyzing preference data, and releasing datasets/code to advance AI model transparency. Requires PhD-level expertise in ML/LLMs and hands-on experience with RLHF/DPO fine-tuning.
Designs and conducts experiments to evaluate AI models using human preference data, develops new metrics and methodologies, and analyzes large-scale interaction data to advance model reliability and alignment.