Role Title: English Speaking Generalist
Role Type: Contractor
Location: Remote
Scope of Work
- Create diverse prompts across a wide range of topics to challenge large language models.
- Submit identical prompts to both ChatGPT and Claude, recording your screen and microphone during the process.
- Verbally articulate comparisons and evaluate outputs from both models in real time, highlighting strengths, weaknesses, and key differences.
- Provide detailed, structured verbal feedback in clear American English, explaining your reasoning and preferences.
- Maintain clarity and professionalism in both spoken and written communication throughout each recording session.
- Interpret provided documentation to ensure consistent evaluation standards and accurate project delivery.
- Collaborate closely with project guidelines to support continuous improvement of AI models.
Preferred Qualifications
- High-level fluency in spoken and written American English, with clear pronunciation and the ability to communicate natural opinions and observations.
- Experience using large language models such as ChatGPT, Claude, Gemini, or similar platforms.
- Familiarity with AI evaluation tasks.
- Comfortable recording screen and audio for extended evaluation sessions in a distraction-free environment.
- Exceptional critical thinking, analytical reasoning, and attention to detail.
- Background in data annotation, AI training, quality assurance, content evaluation, or research is advantageous.
- Strong technical setup, including a reliable computer, stable internet connection, and ability to record high-quality audio and video without issues.