KAWORKS

Senior Voice AI Engineer, Evaluation and Reliability

KAWORKS Responds Quickly
$$$$

We are currently looking for a Senior Voice AI Engineer, Evaluation and Reliability to join a professional German-based product company team that designs innovative eHealth solutions for hospitals.

You will work on a stable healthcare product.

 

Senior level, and we mean it. You would own the evidence that this system is safe to put in front of

patients, on your own judgement, and tell us when the answer is no. That isn't a job we can hand to

someone still learning what to measure.

 

You would not be building a voice stack. We use a third-party voice platform that already handles the

telephony, the speech recognition and synthesis, and the knobs for end-of-speech detection and

interruption. What it does not do is tell us whether any of that is working well enough for patients, and it

gives us no way to check that a change hasn't made things worse. That's the job.

 

So you'd own the conversation and the evidence about it: how the assistant behaves when a caller

interrupts, corrects themselves or won't answer; how fast the whole thing responds once a round trip to

our backend is in the loop; and the body of test cases we run before every change.
 

You need

  • To have operated a phone or voice assistant that answered real calls from real users. You can tell us its response time and how you measured it. Give the response time as a percentile, the figure that most callers experienced or worse, not as an average. We want to know that you know what to measure and what good results look like.
  • To have built a part of a real-time voice pipeline in your own code, or to have changed one in an important way: streaming audio, end-of-speech detection, turn-taking or interruption. A framework such as Pipecat or LiveKit Agents is acceptable. Changing the settings of a closed platform is not enough for this point. In the first months, about half of the role is building our platform.
  • To have tuned a voice system, not only delivered one: end-of-speech detection, barge-in, and how long to wait before the system assumes that the caller has finished. You would do this first with a vendor's settings, and later in our own platform. You would do it on phone audio, where clean barge-in is difficult.
  • To know what happens to speech recognition accuracy when the audio comes through a phone line and not through a good microphone. You have measured this yourself. You did not only read about it.
  • A way to test conversation changes that does not depend on listening to a few calls and hoping that they are good. This is the centre of the role. It can be a replay harness, a scored scenario set or another form. We want to hear how it worked and where it was not good enough.
  • Enough Python to build that harness and the tools around it.
     

Nice to have

  • Experience with a closed voice platform and the problems that it brings, not only with your own system.
  • Telephony background: SIP, WebRTC, Asterisk, Twilio or similar. It helps you understand why calls sound the way they do, but you would not operate any of it.
  • Work with health data, or in another field where mistakes have consequences.
  • German, but we do not depend on it.


You do not need

  • To speak German.
  • To know PHP or our existing backend. Another team builds the endpoints that you would call.
  • To have trained a model from the beginning, without a pre-trained model as the base.

Required skills experience

AI/ML 4 years
Voice AI Agent 2 years
VoIP 2 years

Required domain experience

Healthcare / MedTech 3 years

Required languages

English C1 - Advanced
Ukrainian Native
Published 28 August ยท Updated 29 October
Last 30 days: 302 views ยท 19 applications
All time: 392 views ยท 44 applications
Response activity: High
Last responded yesterday
See stats of candidates who applied for this job ๐Ÿ‘€
To apply for this and other jobs on Djinni login or signup.
Loading...