AI Training Specialist
TextRLHF
As an AI Training Specialist, I engineered and refined prompts to evaluate and enhance Generative AI and conversational models. I conducted RLHF by ranking, rewriting, and fact-checking machine-generated responses to improve factual accuracy across various topics. I identified algorithm bias and safety vulnerabilities in NLP systems to ensure responsible AI development.
• Engineered prompts and conducted prompt evaluation for LLMs
• Performed RLHF tasks, including ranking and fact-checking AI outputs
• Collaborated on taxonomy standards and optimized ML data pipelines
• Conducted model evaluation and quality assurance for accuracy and relevance
As an AI Training Specialist, I engineered and refined prompts to evaluate and enhance Generative AI and conversational models. I conducted RLHF by ranking, rewriting, and fact-checking machine-generated responses to improve factual accuracy across various topics. I identified algorithm bias and safety vulnerabilities in NLP systems to ensure responsible AI development. • Engineered prompts and conducted prompt evaluation for LLMs • Performed RLHF tasks, including ranking and fact-checking AI outputs • Collaborated on taxonomy standards and optimized ML data pipelines • Conducted model evaluation and quality assurance for accuracy and relevance
2020 - Present