AI Training, RLHF, and LLM Evaluation Specialist
TextRLHF
I conducted reinforcement learning from human feedback (RLHF) by systematically evaluating and aligning Large Language Model outputs for accuracy and safety. My responsibilities included designing and administering tests for model outputs, fact-checking responses, and ensuring AI compliance with human value alignment goals. I also contributed to prompt engineering and dataset curation to enhance model training quality and downstream performance.
• Evaluated and rated AI-generated text using internal protocols
• Curated and annotated sample datasets for RLHF pipelines
• Applied prompt engineering for robust model evaluation
• Collaborated on bias detection, safety checks, and QA reviews
I conducted reinforcement learning from human feedback (RLHF) by systematically evaluating and aligning Large Language Model outputs for accuracy and safety. My responsibilities included designing and administering tests for model outputs, fact-checking responses, and ensuring AI compliance with human value alignment goals. I also contributed to prompt engineering and dataset curation to enhance model training quality and downstream performance. • Evaluated and rated AI-generated text using internal protocols • Curated and annotated sample datasets for RLHF pipelines • Applied prompt engineering for robust model evaluation • Collaborated on bias detection, safety checks, and QA reviews
2019 - Present