AI Training Fellow
OtherAudioRLHF
Worked as an AI Training Fellow applying RLHF for multi-modal LLM fine-tuning. Managed feedback alignment across audio, visual, and text data for AI safety and quality. Evaluated generative model responses, enhancing factual accuracy and safety compliance. • Conducted RLHF labeling tasks focused on behavioral model tuning
• Labeled and evaluated sample outputs in audio, text, and visual domains
• Collaborated remotely under strict AI safety and accuracy guidelines
• Adapted to dynamic project requirements and updated labeling instructions regularly
Worked as an AI Training Fellow applying RLHF for multi-modal LLM fine-tuning. Managed feedback alignment across audio, visual, and text data for AI safety and quality. Evaluated generative model responses, enhancing factual accuracy and safety compliance. • Conducted RLHF labeling tasks focused on behavioral model tuning • Labeled and evaluated sample outputs in audio, text, and visual domains • Collaborated remotely under strict AI safety and accuracy guidelines • Adapted to dynamic project requirements and updated labeling instructions regularly
2026 - Present