Senior AI Training Specialist
TextRLHF
As Senior AI Training Specialist at Outlier, I led the fine-tuning of LLMs for high-persona creative tasks and improvement of narrative flow through RLHF. I managed a 10+ person team, implementing feedback loops to assure high accuracy in model alignment and safety. I authored an annotation playbook to streamline onboarding and enhance data integrity across labeling operations.
• Oversaw supervised fine-tuning and RLHF for creative narrative tasks.
• Developed ethical annotation guidelines and provided mentorship to AI tutors.
• Achieved 95%+ model alignment accuracy through continuous evaluation.
• Collaborated to detect bias and refine model safety.
As Senior AI Training Specialist at Outlier, I led the fine-tuning of LLMs for high-persona creative tasks and improvement of narrative flow through RLHF. I managed a 10+ person team, implementing feedback loops to assure high accuracy in model alignment and safety. I authored an annotation playbook to streamline onboarding and enhance data integrity across labeling operations. • Oversaw supervised fine-tuning and RLHF for creative narrative tasks. • Developed ethical annotation guidelines and provided mentorship to AI tutors. • Achieved 95%+ model alignment accuracy through continuous evaluation. • Collaborated to detect bias and refine model safety.
2025 - 2026