Handshake AI Fellow – RLHF/Evaluation/Rating Specialist
OtherText
As a Handshake AI Fellow, I systematically compared and ranked AI-generated solutions to complex problems. My work involved providing expert written justifications and detailed feedback to improve large language models. This role focused on enhancing AI systems through expert human evaluation and preference ranking.
• Compared and rated AI-generated answers using established criteria.
• Identified and flagged formatting issues in code and markdown/LaTeX.
• Provided written justifications to guide AI model improvements.
• Directly contributed to the RLHF (Reinforcement Learning from Human Feedback) processes.
As a Handshake AI Fellow, I systematically compared and ranked AI-generated solutions to complex problems. My work involved providing expert written justifications and detailed feedback to improve large language models. This role focused on enhancing AI systems through expert human evaluation and preference ranking. • Compared and rated AI-generated answers using established criteria. • Identified and flagged formatting issues in code and markdown/LaTeX. • Provided written justifications to guide AI model improvements. • Directly contributed to the RLHF (Reinforcement Learning from Human Feedback) processes.
2025 - 2025