Back to all jobs
I
About the role
<p></p>
<div>A project dedicated to assessing and benchmarking advanced agentic audio models against leading systems. The program’s mission is to evaluate and optimize model performance for real-world customer support use cases.<br>Responsibilities</div>
<ul>
<li>Create and execute <strong>role-play–based evaluation scenarios</strong> that simulate realistic customer service interactions across multiple domains, including:
<ul>
<li>Flight bookings and travel support</li>
<li>Financial services</li>
<li>Telecommunications and technical support</li>
</ul>
</li>
<li>Contribute to the development of <strong>diverse and representative datasets</strong> used to assess conversational audio agents.</li>
<li>Evaluate model performance across a standardized set of qualitative and quantitative metrics.</li>
<li>Ensure evaluations reflect real customer expectations for clarity, efficiency, and natural conversational flow.</li>
</ul>
<div><br>Evaluation Metrics<br>Model performance is assessed using a combination of conversational, technical, and audio-specific criteria, including but not limited to:</div>
<ul>
<li><strong>Task completion accuracy</strong> and efficiency</li>
<li><strong>Conversational naturalness</strong> (tone, flow, and coherence)</li>
<li><strong>Audio comprehension and response quality</strong></li>
<li><strong>Instruction adherence and contextual understanding</strong></li>
<li><strong>Basic computer programming literacy</strong>, including:
<ul>
<li>Understanding of <strong>JSON structures</strong></li>
<li>Familiarity with <strong>functions and methods</strong></li>
<li>Ability to reason about structured data and simple logic</li>
</ul>
</li>
<li><strong>Technical communication clarity</strong> when handling support-style problem-solving</li>
</ul>
<div><br>Technical & Equipment Requirements</div>
<ul>
<li>Strong verbal communication skills in a simulated customer support context</li>
<li>English proficiency including fluency across all language skills: reading, listening, writing, and speaking.</li>
<li>Access to a <strong>high-quality microphone</strong> to ensure clean, reliable audio input during evaluations</li>
<li>Comfort working with structured prompts, evaluation rubrics, and technical guidelines</li>
<li>Device capable of running audio recording software and opening large technical documentation</li>
</ul>
<p>We offer a pay range of $11-to- $30.65 per hour, with the exact rate determined after evaluating your experience, expertise, and geographic location. Final offer amounts may vary from the pay range listed above. As a contractor you’ll supply a secure computer and high‑speed internet; company‑sponsored benefits such as health insurance and PTO do not apply.</p>
<p>Employment type: Contract<br>Workplace type: Remote<br>Seniority level: Mid‑Senior Level</p>
Perks & benefits
- Medical Insurance
- Paid Time Off
755,000+ hidden jobs like this
Invisible Agency and thousands of companies post here first — often days before LinkedIn or Indeed. Your first 5 applications are free; go Pro to apply without limits.
Everything Pro unlocks:
- Unlimited applications — free stops at 5
- Track every application in one place
- Apply straight to the source, one click
- Save & organize roles you love
- Roles pulled from company boards before the big sites