AI/LLM Model Trainer & Evaluator
TextRLHF
I evaluated outputs from large language models (LLMs) for accuracy, relevance, and alignment with quality standards. I performed prompt engineering, identified model failures, and engaged in iterative review and improvement of outputs across text, voice, and image models. I also participated in Reinforcement Learning from Human Feedback (RLHF) training by undertaking preference ranking and annotation tasks.
• Conducted prompt evaluation and design for LLMs
• Rated and reviewed outputs for alignment and quality
• Annotated edge cases and model failures for retraining
• Assessed voice and image model generations for user experience
I evaluated outputs from large language models (LLMs) for accuracy, relevance, and alignment with quality standards. I performed prompt engineering, identified model failures, and engaged in iterative review and improvement of outputs across text, voice, and image models. I also participated in Reinforcement Learning from Human Feedback (RLHF) training by undertaking preference ranking and annotation tasks. • Conducted prompt evaluation and design for LLMs • Rated and reviewed outputs for alignment and quality • Annotated edge cases and model failures for retraining • Assessed voice and image model generations for user experience
2024 - Present