About the role
CoreReach builds AI voice agents that answer calls for property management companies, day or night. When a resident calls at 2 AM, the agent has to understand them, decide whether it's a real emergency, reach the right person, and leave the team a clear record of what happened.
As an AI Voice Engineer, you'll own how our agents behave on a call: how they listen, what they say, when they escalate, and how we prove they got it right. This is a remote role, open to candidates in the US.
What you'll do
- Design and improve the conversation logic behind our voice agents, from greeting to handoff
- Build the rules that decide what counts as an emergency and who gets called
- Keep the agent's answers accurate and fair-housing safe, with guardrails that hold on every call
- Build evaluation tooling and test suites that catch problems before customers hear them
- Tune prompts, models and settings for faster, more natural conversations
- Monitor call quality in production and debug issues across the voice, telephony and model layers
- Work with product and customer success to turn customer requests into agent behavior
What we're looking for
- 3+ years building software, including production products powered by LLMs
- Strong Python or TypeScript skills
- Hands-on experience with prompt design, evaluation and structured output from LLMs
- Familiarity with speech-to-text and text-to-speech systems
- Good judgment about edge cases, and the habit of testing for them
- Comfort working across the full stack when needed
Nice to have
- Experience with telephony (SIP, WebRTC) or real-time audio
- Experience building evaluation frameworks for generative AI systems
- Voice AI or conversational agents shipped to production
- Background in property management, customer support or call centers
What we offer
- Competitive salary and equity
- Fully remote work with flexible hours
- Health, dental and vision insurance
- Generous PTO and company holidays
- Home office stipend
- Ownership of how our agents behave on every call