AI Training Specialist | Outlier
TextRLHF
Served as an AI Training Specialist performing RLHF to enhance the safety and accuracy of generative AI models. My responsibilities included evaluating Large Language Models for accuracy, logical reasoning, and linguistic nuance to generate high-quality training datasets. I applied my bilingual proficiency to provide human feedback across diverse subject matters in both English and Spanish. • Conducted ranking, scoring, and evaluation of model outputs using specific rubrics.
• Developed and tested prompts to probe model boundaries and mitigate hallucinations.
• Performed data quality assurance by rigorous fact checking and logical analysis of outputs.
• Interfaced with internal/proprietary tooling for data labeling and feedback loops.
Served as an AI Training Specialist performing RLHF to enhance the safety and accuracy of generative AI models. My responsibilities included evaluating Large Language Models for accuracy, logical reasoning, and linguistic nuance to generate high-quality training datasets. I applied my bilingual proficiency to provide human feedback across diverse subject matters in both English and Spanish. • Conducted ranking, scoring, and evaluation of model outputs using specific rubrics. • Developed and tested prompts to probe model boundaries and mitigate hallucinations. • Performed data quality assurance by rigorous fact checking and logical analysis of outputs. • Interfaced with internal/proprietary tooling for data labeling and feedback loops.
2021 - Present