AI Trainer & Prompt Engineer (Freelance)
TextRLHF
As a freelance AI Trainer & Prompt Engineer, I designed and evaluated complex prompts for leading LLMs, focusing on reasoning and safety. I conducted red-teaming exercises and contributed systematic feedback for safer and more effective AI models. I ranked and rated model outputs, developed prompt templates, and organized evaluation documentation.
• Evaluated LLM responses across coding, creative writing, summarization, and multi-step reasoning.
• Conducted structured written feedback to address model vulnerabilities and improve model safety.
• Assisted in RLHF pipelines using accuracy, helpfulness, and harmlessness rubrics.
• Developed reusable evaluation frameworks for peers and wider adoption.
As a freelance AI Trainer & Prompt Engineer, I designed and evaluated complex prompts for leading LLMs, focusing on reasoning and safety. I conducted red-teaming exercises and contributed systematic feedback for safer and more effective AI models. I ranked and rated model outputs, developed prompt templates, and organized evaluation documentation. • Evaluated LLM responses across coding, creative writing, summarization, and multi-step reasoning. • Conducted structured written feedback to address model vulnerabilities and improve model safety. • Assisted in RLHF pipelines using accuracy, helpfulness, and harmlessness rubrics. • Developed reusable evaluation frameworks for peers and wider adoption.
2023 - Present