AI Trainer
Internal Proprietary ToolingTextRLHF
As an AI Trainer at Outlier AI, I performed RLHF and SFT on frontier LLMs, emphasizing complex reasoning tasks. I executed evaluations of model-generated video and text data for temporal consistency and motion accuracy. I provided detailed model rankings and qualitative feedback for ongoing model refinement.• Specialized in prompt engineering and model ranking for LLMs
• Evaluated video outputs for adherence to complex text prompts
• Assessed model responses for truthfulness, helpfulness, and safety
• Contributed to iterative model improvement cycles
As an AI Trainer at Outlier AI, I performed RLHF and SFT on frontier LLMs, emphasizing complex reasoning tasks. I executed evaluations of model-generated video and text data for temporal consistency and motion accuracy. I provided detailed model rankings and qualitative feedback for ongoing model refinement.• Specialized in prompt engineering and model ranking for LLMs • Evaluated video outputs for adherence to complex text prompts • Assessed model responses for truthfulness, helpfulness, and safety • Contributed to iterative model improvement cycles
2025