Freelance AI Prompt Engineer & LLM Evaluator
TextRLHF
Served as an AI Prompt Engineer and LLM Evaluator, contributing to datasets for next-generation Large Language Models using RLHF and SFT methodologies. Designed high-quality prompts across reasoning, coding, Q&A, and multimodal tasks, including text, image, audio, and video. Conducted structured evaluation and quality analysis, ensuring high dataset consistency, safety, and policy alignment.
• Evaluated model outputs for correctness, helpfulness, and safety.
• Performed QA reviews on prompts and annotations for data integrity.
• Created advanced, edge-case prompts to stress-test LLMs.
• Supported model alignment and flagged unsafe outputs.
Served as an AI Prompt Engineer and LLM Evaluator, contributing to datasets for next-generation Large Language Models using RLHF and SFT methodologies. Designed high-quality prompts across reasoning, coding, Q&A, and multimodal tasks, including text, image, audio, and video. Conducted structured evaluation and quality analysis, ensuring high dataset consistency, safety, and policy alignment. • Evaluated model outputs for correctness, helpfulness, and safety. • Performed QA reviews on prompts and annotations for data integrity. • Created advanced, edge-case prompts to stress-test LLMs. • Supported model alignment and flagged unsafe outputs.
2024 - Present