Senior Voice AI Engineer - Pipecat / LiveKit — production voice agent, EU-hosted stack

Posted yesterday

Worldwide

Summary

We've built a voice agent that triages repair faults over the phone for UK social housing tenants. A tenant rings in, no app, the agent works out what's actually wrong with the boiler or the damp, and an engineer receives a diagnostic brief. It's live and taking calls. It now needs to be production-grade before it speaks to a real tenant, and that's the work. STACK Pipecat 0.0.108, self-hosted LiveKit, Speechmatics (EU1), Mistral (Paris), Sinch, Python 3.12, Hetzner + Coolify. Everything EU-hosted. No US-owned managed services anywhere in the pipeline. That's not a preference — it's a procurement requirement for our customers and it's most of why the product exists. WHAT NEEDS BUILDING — An eval harness for the conversation layer — A tree-execution engine: a state machine where the LLM does edge selection only, and never invents a node or a diagnosis — A deterministic safety gate that runs alongside the LLM and can veto it — Async photo evidence: a vision model extracts into a closed vocabulary and feeds the tree as answers, never as a diagnosis — Sinch telephony finished to production quality FIRST ENGAGEMENT Two weeks, paid, building the eval harness. Real deliverable, separable, and it's the thing everything else depends on. If it goes well: 3 days a week for six months, then a conversation about something permanent. MUST HAVE — Built a voice agent that took real phone calls. Not a demo. Pipecat, LiveKit Agents, Vapi, Retell or equivalent. — Strong Python async — Experience making an LLM produce reliable structured output under constraint — Have built an eval harness for an LLM system before, not just used one — Comfortable running self-hosted infrastructure USEFUL — SIP / telephony (Sinch, Twilio, Telnyx) — Vision models extracting structured facts from images — Multilingual ASR in production — Have worked somewhere that safety mattered NOT NEEDED Housing knowledge. Frontend. UK public sector experience. We handle all of that. TIMEZONE EU or UK hours. Remote.

  • Less than 30 hrs/week
    Hourly
  • 3-6 months
    Duration
  • Expert
    Experience Level
  • $90.00

    -

    $130.00

    Hourly
  • Remote Job
  • Complex project
    Project Type

Contract-to-hire opportunity

This lets talent know that this job could become full time.
Learn more
Skills and Expertise
Mandatory skills
Python
Conversational AI
Activity on this job
  • Proposals:5 to 10
  • Last viewed by client:13 minutes ago
  • Interviewing:
    3
  • Invites sent:
    0
  • Unanswered invites:
    0
About the client
Member since Jul 9, 2026
  • United Kingdom
    8:17 PM

Explore similar jobs on Upwork

Voice Acting
Female
Male
2D Animation
Narrator for Storytelling YouTube ChannelFixed-price‐ Posted 1 month ago
Voice Acting
Singing
Audio Production
Music

How it works

  • Post a job icon
    Create your free profile
    Highlight your skills and experience, show your portfolio, and set your ideal pay rate.
  • Talent comes to you icon
    Work the way you want
    Apply for jobs, create easy-to-by projects, or access exclusive opportunities that come to you.
  • Payment simplified icon
    Get paid securely
    From contract to payment, we help you work safely and get paid securely.
Want to get started? Create a profile

About Upwork

  • Rating is 4.9 out of 5.
    4.9/5
    (Average rating of clients by professionals)
  • G2 2021
    #1 freelance platform
  • 49,000+
    Signed contract every week
  • $2.3B
    Freelancers earned on Upwork in 2020

Find the best freelance jobs

Growing your career is as easy as creating a free profile and finding work like this that fits your skills.

Trusted by

  • Microsoft Logo
  • Airbnb Logo
  • Bissell Logo
  • GoDaddy Logo