Freelance English Writer - AI Trainer

About This Role

This project-based role involves engaging in realistic multi-turn conversations with large language models (LLMs) to test and improve their capabilities. You will act as a controlled adversary, crafting plausible human dialogue to expose subtle model weaknesses and evaluate their responses.

Responsibilities

• Put yourself in various user personas to engage in realistic multi-turn conversations with LLMs
• Use a range of tones and registers in interactions
• Stress-test models' ability to respond adequately based on abstract dimensions (instruction-following, emotional intelligence, consistency)
• React and adapt to model output while maintaining focus on task requirements
• Think like a storyteller and a tester to expose model weaknesses
• Understand human speech patterns, hesitations, contradictions, and emotional escalations
• Deliberately engineer conversational pressure without breaking realism
• Methodically document observations clearly and consistently
• Pinpoint failure modes and LLM patterns

Requirements

• C2-level English (CPE, TOEFL 114+, IELTS 8.0 or above)

Qualifications

• Under- or postgraduate qualification in an Arts-based subject (English, Creative Writing, Journalism, MFL, Psychology, Cognitive Science), related field, or work experience at an equivalent level
• 1+ years' experience in Conversational AI Testing, Narrative Design, or Adversarial Model Testing

Nice to Have

• Conversational UX / dialogue design experience
• Understanding of prompt engineering or LLM evaluation
• Experience with QA testing for complex systems
• Background in narrative design, interactive fiction, or screenwriting
• Qualification in, or professional experience with, behavioural research, psychology, or linguistics
• Demonstrated familiarity with LLM behaviour, failure modes, and evaluation concepts
• Experience working with structured guidelines, rubrics, or annotation frameworks