This list contains only the countries for which job offers have been published in the selected language (e.g., in the French version, only job offers written in French are displayed, and in the English version, only those in English).
We are looking for an AI QA Engineer to ruthlessly test our digital employees ability to listen, think, and speak in real-time. Any delay or logical glitch breaks the magic; your mission is to ensure it stays seamless.
Job Responsibility:
Voice UX Testing: Measure and optimize Latency (P95/P99). Verify Barge-In functionality: ensure the agent stops speaking immediately when interrupted, even in noisy environments
Logic & Flow Validation: Read and understand NSL (Jinja2) scripts to identify potential logical loops or dead ends. Verify that the agent handles state transitions correctly (e.g., booking created -> confirmation sent)
Hallucination Control: Detect when the AI drifts from its instructions or invents facts. Help build "Golden Datasets" of correct conversations for regression testing
Integration Testing: Verify that the agent correctly triggers external tools (e.g., CRM updates) during a call. What happens if the API fails? Does the agent handle it gracefully?
Requirements:
2+ years of hands-on experience in manual testing
Ability to read code (Python, Jinja2) and work confidently with JSON data payloads to better understand test scenarios
Understanding of STT (Speech-to-Text), TTS (Text-to-Speech), and VAD (Voice Activity Detection) concepts, including the importance of silence detection
Strong exploratory testing mindset with the ability to intentionally stress and challenge AI agents (e.g., interruptions, rapid speech, topic switching, unclear pronunciation)
Russian - Native or Fluent
English - Upper-Intermediate (B2+)
Nice to have:
Experience with LLM prompting
Experience testing voice assistants (Alexa, Google Assistant)