Multi-modal AI Training Specialist
VideoRLHF
Specialized in RLHF for multi-modal AI models, focusing on Video and Image-to-Text evaluation. My role involves ranking AI responses for logical consistency, safety, and factual accuracy. I apply professional rigor from my background in logistics and clinical laboratory analysis to identify complex edge cases and errors in high-level reasoning environments like Triton.
Specialized in RLHF for multi-modal AI models, focusing on Video and Image-to-Text evaluation. My role involves ranking AI responses for logical consistency, safety, and factual accuracy. I apply professional rigor from my background in logistics and clinical laboratory analysis to identify complex edge cases and errors in high-level reasoning environments like Triton.
2024 - Present