Job descriptionThis is a remote, hourly-paid contractor role where you will interact with a speech-based AI model through short, natural conversations and then evaluate the model’s performance. You’ll speak to the model in everyday scenarios (e.g., acting as a customer while the model plays a flower shop) for approximately 5 minutes per session, then answer structured questions about response quality, accuracy, helpfulness, and conversational naturalness. SME Careers is a fast-growing AI Data Services company and a subsidiary of SuperAnnotate, providing AI training data for many of the world’s largest AI companies and foundation-model AI labs. Your work directly helps improve cutting-edge speech and conversational AI systems through rigorous testing and clear, high-quality feedback. Key Responsibilities: • Conduct Speech-Based Scenario Conversations: Speak with the AI model in guided real-world use cases (e.g., shopping, customer support, making appointments), maintaining a natural conversation for ~5 minutes per session. • Evaluate Model Performance: Answer follow-up questions assessing the model’s quality (e.g., accuracy, relevance, clarity, politeness, and ability to complete the task). • Provide High-Quality Written Feedback: Write concise, specific notes on what worked well and what failed (e.g., misunderstandings, incorrect assumptions, awkward phrasing, conversation breakdowns). • Follow Rubrics and Guidelines: Apply evaluation criteria consistently across sessions and adhere to task instructions. Your Profile: • Must be currently living in the United States. • Fluent in English (spoken, reading, and writing). • Strong reading and writing skills with the ability to provide clear, detailed feedback. • Comfortable speaking naturally and clearly on microphone for short sessions. • Detail-oriented, consistent, and able to follow task instructions and evaluation rubrics. • Reliable internet connection and access to a quiet environment for speaking tasks.
