Advanced AI Data Trainer – Invisible Technologies
As an Advanced AI Data Trainer at Invisible Technologies, I performed supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF) for improving AI model alignment and performance. My work involved evaluating and ranking AI-generated responses and engaging in error labeling and red teaming to ensure quality. I also applied prompt engineering and criteria-based verification to optimize outputs. • Conducted SFT and RLHF for model improvement • Evaluated and ranked AI responses on accuracy and clarity • Labeled errors and engaged in red teaming tasks • Applied criteria-based consistency checks