Technical STEM content Evaluator & AI Trainer
TextRLHF
Performed high-fidelity Reinforcement Learning from Human Feedback (RHLF) and technical fact checking for complex STEM prompts. My work focused on validating model outputs related to thermodynamics, fluid mechanics, and internal combustion engine design.
Performed high-fidelity Reinforcement Learning from Human Feedback (RHLF) and technical fact checking for complex STEM prompts. My work focused on validating model outputs related to thermodynamics, fluid mechanics, and internal combustion engine design.
2025 - Present