🛠 Tech Stack

💼 About This Role

You'll design and evaluate structured conversational scenarios to test advanced agentic audio models for real-world customer support across industries like travel and finance. Your work will directly contribute to dataset creation and model benchmarking for next-generation voice AI.

🎯 What You'll Do

• Design and execute role-play scenarios simulating customer support conversations.
• Evaluate AI model outputs using standardized qualitative and quantitative criteria.
• Assess conversational quality including clarity, flow, tone, and naturalness.
• Validate task completion accuracy, contextual understanding, and instruction adherence.

📋 Requirements

• English proficiency across reading, writing, listening, and speaking.
• Experience in simulated customer support or conversational environments.
• Ability to evaluate structured dialogue and follow detailed assessment frameworks.
• Basic understanding of structured data concepts such as JSON and simple logic reasoning.

✨ Nice to Have

• Reliable access to a high-quality microphone for audio-based assessments.
• Device capable of handling audio recording tools and technical materials.

🎁 Benefits & Perks

• 💰 Hourly compensation: $11 – $30.65 per hour
• 🏠 Remote contract with flexible working arrangements
• 🤖 Cutting-edge AI model development exposure
• 📝 Project-based work with clear evaluation frameworks

📨 Hiring Process

Estimated timeline: 2-3 weeks · AI estimate

1. 1Application Review· 1 week
2. 2Phone Screen· 30 min
3. 3Technical Assessment· 1 hour