AI Content Specialist / Red Teamer
OtherTextRed Teaming
As an AI Content Specialist and Red Teamer, I executed adversarial testing on LLMs to identify failure modes and ensure safety. My work included rigorous grading of model outputs and the curation of advanced datasets for model fine-tuning. I also developed and validated training data for specialized reasoning tasks in global research labs.
• Performed adversarial red-teaming of LLMs in multi-turn conversations.
• Graded language model outputs using complex ranking rubrics for factuality and coherence.
• Created and validated 'Golden Set' datasets for LLM fine-tuning.
• Applied Chain of Thought prompting to test and correct advanced model logic.
As an AI Content Specialist and Red Teamer, I executed adversarial testing on LLMs to identify failure modes and ensure safety. My work included rigorous grading of model outputs and the curation of advanced datasets for model fine-tuning. I also developed and validated training data for specialized reasoning tasks in global research labs. • Performed adversarial red-teaming of LLMs in multi-turn conversations. • Graded language model outputs using complex ranking rubrics for factuality and coherence. • Created and validated 'Golden Set' datasets for LLM fine-tuning. • Applied Chain of Thought prompting to test and correct advanced model logic.
2024 - Present