AI Engineer - Voice

About the role

Skills: Prompt Engineering, JavaScript, Node.js, React, Chatbots

The Mission

We're building an AI-powered insurance brokerage transforming the $900B commercial insurance market. Voice is our primary growth lever - the majority of insurance transactions happen over phone calls. We need an exceptional Head of Voice AI to architect voice systems that will power thousands of conversations daily across growth, sales, operations, and customer service. You'll use low-code platforms like VAPI or Retell for quick prototyping and rapid deployment of production voice agents, then progressively build custom infrastructure using LiveKit and Pipecat as we scale. Your systems will handle everything from cold outreach and lead qualification to complex multi-turn underwriting conversations and 24/7 customer support. We're committed to "Staying REAL" with our AI systems - building agents that are Reliable, Experience-focused, Accurate, and have Low latency. You'll work directly with the CEO and CTO with a bias toward action. We live by core principles: "There is no try, there is just do," "Actions lead to information, always default to action," and "Strong opinions lead to information."

Outcomes You'll Drive

Voice Infrastructure & Scale

Deploy production voice agents within weeks using VAPI or Retell for quick prototyping and immediate business impact

Transition to custom voice infrastructure with LiveKit and Pipecat as volume scales

Achieve sub-700ms latency across the entire voice pipeline while maintaining conversation quality

Scale to 10,000+ concurrent calls with appropriate architecture evolution and optimization

Integrate telephony at scale with Twilio, Telnyx, and enterprise SIP infrastructure

Growth & Sales Automation

Build outbound prospecting agents that identify qualified leads, overcome objections, and book appointments

Create lead nurturing systems with personalized follow-ups that move prospects through the sales funnel

Implement predictive dialing and call pacing algorithms for maximum efficiency

Design qualification workflows that gather key information and route to appropriate human agents

Operations & Underwriting Support

Develop form-filling agents handling 20-30 minute insurance application conversations

Build underwriter follow-up systems that collect additional risk information through natural, multi-turn dialogue

Create document collection workflows guiding customers through providing licenses, photos, and business documentation

Implement intelligent escalation paths that know when to loop in human underwriters

Customer Service Excellence

Design 24/7 policy servicing agents that explain coverage, generate certificates, and process endorsements

Build claims intake systems that empathetically gather first notice of loss (FNOL) information

Create payment processing agents handling failed payments, billing updates, and payment plans

Develop proactive outreach systems for policy renewals, payment reminders, and important updates

Platform Development

Create no-code/low-code tools enabling non-technical teams to create and modify voice workflows

Build conversation analytics tracking quality metrics, completion rates, and customer satisfaction

Develop A/B testing frameworks for voice personas, prompts, and conversation strategies

Implement voice agent templates for common insurance workflows

Create comprehensive monitoring to track latency, accuracy, and conversation outcomes

You're Our Person If

If You've built production voice AI systems handling 100K+ minutes per month with real customers You have hands-on experience with low-code platforms (VAPI, Retell) for rapid prototyping and custom voice infrastructure (LiveKit, Pipecat) for scale You understand the full voice stack from telephony protocols to WebRTC-based media servers You've optimized voice pipelines achieving sub-second latency while maintaining quality You can architect systems that maintain context through 30+ minute conversations You've built both inbound and outbound calling systems at scale You have experience with modern STT/TTS providers and know how to optimize them You ship voice features daily and iterate based on real conversation data You balance starting with practical solutions while building toward technical excellence You understand that voice AI is about business impact, not just technical sophistication You embrace "there is no try, there is just do" as your engineering mantra

Hard Requirements

5+ years of software engineering experience with at least 3 years deeply focused on voice/audio systems

Production voice AI experience - you've built and deployed systems handling 10K+ minutes/month

Hands-on experience with low-code voice platforms like VAPI or Retell for rapid prototyping

Deep understanding of telephony and media protocols including SIP, RTP, and WebRTC

Experience with voice orchestration frameworks like LiveKit, Pipecat, Daily, or custom-built solutions

Advanced audio processing knowledge - you understand VAD, AEC, noise suppression at a technical level

Proven ability to achieve sub-second latency in production voice systems

Strong proficiency in Python and TypeScript/Node.js specifically for real-time systems

Experience with both inbound and outbound calling at scale (1000+ concurrent calls)

Modern AI provider expertise with OpenAI, Anthropic, Deepgram, ElevenLabs, etc.

Track record of shipping voice products that directly impact business metrics

Strong debugging skills for complex, multi-service voice pipelines

Must be based in San Francisco and work in-office (relocation assistance provided)

Our Voice Tech Stack

Rapid Prototyping & Deployment: VAPI or Retell for quick prototyping and initial voice agent deployment Twilio and Telnyx for telephony infrastructure Deepgram and AssemblyAI for ultra-low latency speech-to-text ElevenLabs and Cartesia for natural text-to-speech GPT-4o and Gemini for conversational intelligence Custom Infrastructure (Scale To): LiveKit for WebRTC-based real-time media infrastructure Pipecat for flexible voice pipeline orchestration Custom orchestration layers for complex conversation management Redis streams for audio buffering and event processing PostgreSQL for conversation history and analytics Temporal.io for durable conversation workflows tools Logfire for comprehensive observability

What You'll Build in Your First 90 Days

First Month: Deploy your first outbound calling agent using VAPI or Retell for quick prototyping Build information collection agents for gathering initial customer data Implement payment reminder system that handles failed payments and billing updates Create conversation recording pipeline for quality monitoring and compliance Set up A/B testing framework for different voice personas and scripts Establish baseline metrics for conversation success rates

Second Month: Build comprehensive form-filling agent capable of 20-30 minute insurance applications Implement underwriter follow-up system collecting additional information through dialogue Create multi-modal orchestration allowing seamless handoffs between voice, SMS, and email Develop claims intake agent with empathetic conversation handling Build certificate generation system accessible 24/7 through voice commands Begin transition to custom infrastructure for high-volume use cases

Third Month: Scale outbound infrastructure to handle 1000+ concurrent prospecting calls Build complete customer service suite covering policy changes, endorsements, and inquiries Implement intelligent routing system directing calls to specialized agents Develop predictive models for optimal call timing and conversation success Create voice agent templates for non-technical team members Launch production campaigns measuring impact on conversion and satisfaction

Our Voice AI Philosophy

Start Practical, Scale Smart : Begin with low-code platforms for rapid deployment, build custom infrastructure as needed Voice is the Channel : Recognize that voice is how insurance happens - optimize for natural conversation Latency is Everything : Sub-700ms response times or we've failed Revenue Impact First : Every voice interaction should drive conversion, retention, or efficiency Context Preservation : Maintain full context even across 30+ minute calls Fail Gracefully : Always have intelligent fallbacks and recovery mechanisms Data-Driven Iteration : Measure everything, iterate based on real conversations Ship Daily : Deploy quickly, learn fast, improve continuously REAL Framework : Every interaction must be Reliable, Experience-focused, Accurate, and Low-latency

Join Us To Transform Insurance

This is an early-stage role at a fast-moving startup where you'll define how voice AI transforms insurance. Voice is our biggest point of leverage - you'll directly impact how we scale 10x without proportional headcount increases. You'll start with practical solutions that work today, then build the infrastructure to scale tomorrow. You should have experience building voice AI systems that real customers use at scale - handling thousands of calls per day, maintaining sub-second latency, and gracefully handling all the edge cases that come with production voice systems. We value engineers who ship daily and measure success by business impact, not technical complexity. We require you to be in San Francisco and work from our office 5.5 days per week. We'll cover relocation costs and believe the best teams collaborate intensively in person.