AI Training Specialist (Multimodal & Psychological Alignment)
TextFine Tuning
As an AI Training Specialist at Outlier AI, I train and refine large language models and multimodal AI systems. My work includes data labeling, supervised fine-tuning, and reinforcement learning from human feedback, spanning text, image, and audio projects. I develop high-quality datasets for specialized domains, especially psychological alignment, and also handle generalist data labeling tasks.
• Performed data labeling and annotation across text, image, and audio inputs
• Applied RLHF to advance LLM alignment in psychological contexts
• Built and maintained high-quality, diverse datasets for model training
• Refined datasets for both general and specialized use cases
As an AI Training Specialist at Outlier AI, I train and refine large language models and multimodal AI systems. My work includes data labeling, supervised fine-tuning, and reinforcement learning from human feedback, spanning text, image, and audio projects. I develop high-quality datasets for specialized domains, especially psychological alignment, and also handle generalist data labeling tasks. • Performed data labeling and annotation across text, image, and audio inputs • Applied RLHF to advance LLM alignment in psychological contexts • Built and maintained high-quality, diverse datasets for model training • Refined datasets for both general and specialized use cases
2025 - Present