Technical Content Evaluator & AI Trainer
OtherTextRLHF
As a Technical AI Tutor and Content Evaluator, I reviewed and rated over 1,000 AI-generated responses for mathematical and technical validity. I ranked, fact-checked, and assessed outputs from Large Language Models (LLMs), focusing on the accuracy, helpfulness, and safety of responses in complex technical domains. My work contributed directly to reinforcement learning from human feedback and fine-tuning technical language models. • Evaluated and rated multi-turn conversations and coding responses
• Performed red teaming and adversarial prompt engineering for AI robustness
• Verified model hallucinations and technical 'Ground Truth' data
• Localized technical concepts for regional contextualization in Yoruba
As a Technical AI Tutor and Content Evaluator, I reviewed and rated over 1,000 AI-generated responses for mathematical and technical validity. I ranked, fact-checked, and assessed outputs from Large Language Models (LLMs), focusing on the accuracy, helpfulness, and safety of responses in complex technical domains. My work contributed directly to reinforcement learning from human feedback and fine-tuning technical language models. • Evaluated and rated multi-turn conversations and coding responses • Performed red teaming and adversarial prompt engineering for AI robustness • Verified model hallucinations and technical 'Ground Truth' data • Localized technical concepts for regional contextualization in Yoruba
2023 - Present