AI Trainer & Model Evaluation Specialist (RLHF)
TextRLHF
Conducted high-complexity data annotation and response evaluation for frontier LLMs. My primary focus involved RLHF(Reinforcement learning from human feedback) and ELO- style head-to -head rankings to improve model safety , factuality, and reasoning capabilities .
Conducted high-complexity data annotation and response evaluation for frontier LLMs. My primary focus involved RLHF(Reinforcement learning from human feedback) and ELO- style head-to -head rankings to improve model safety , factuality, and reasoning capabilities .
2025 - Present