Prompt Engineer & AI Data Annotator (LLM Evaluation)
I worked as a prompt engineer and AI trainer on the Outlier platform, where I was responsible for creating, testing, and refining prompts to improve large language model (LLM) performance. My role involved evaluating AI-generated responses for accuracy, relevance, and quality, and providing structured feedback to enhance model outputs. I followed detailed guidelines to ensure consistency and alignment with expected standards. I also performed data annotation tasks, including categorising responses, identifying errors, and improving prompt-response interactions. This required strong attention to detail, critical thinking, and the ability to interpret complex instructions. Through this work, I developed skills in prompt design, quality assurance, and AI response evaluation, contributing to the overall improvement of model performance.