Voice Experience Designer, Agentic Voice

Your role
As a Voice Experience (VX) Designer, you'll own the voices, personalities, and interactions that make an AI agent feel intuitive, empathetic, and human. We're going all-in on agentic AI under one core idea: stop answering, start resolving. A voice agent that resolves is only as good as the experience it delivers; designing that entire voice experience is your job.

Reporting directly to the VP of AI Products, you'll define the personas, standards, and quality bar that our Speech engineering team implements and that forward-deployed VX designers apply account-by-account in the field. You author the voice; they build the machine that renders it, and the field applies it. You'll collaborate hand-in-hand with our AI engineers to shape model judgment through prompts and flow orchestration rather than hard-coded branches.

You'll bring a deep sense of behavioral and emotional design to the platform, ensuring our agents have the taste, pacing, and vocabulary to sound truly competent and empathetic across both happy paths and high-stakes moments.

This position has the opportunity to be based in our Bay Area office.

What you’ll do

• Own the persona: Define the agent's global voice, character, and personality, and maintain persona consistency across every vertical we ship.
• Set the voice palette & house standards: Establish the standards for pacing, prosody, and emphasis that Speech engineering implements and forward-deployed teams apply to build brand-specific experiences.
• Define the quality bar: Own the universal platform quality bar — Consistency, Fluency, perceived Latency and acceptable trade-offs — and tie persona decisions directly to core metrics like resolution, containment, and sentiment.
• Design behavior with prompts: Partner with AI engineers to orchestrate escalation instincts, confirmation patterns, and graceful recovery using advanced prompting rather than rigid dialogue trees — expressing design intent that alters model outputs without writing code.
• Own handoff & turn-taking experience: Design standard handoff patterns where context is fully preserved when an agent passes a caller to a human, and shape turn-taking and barge-in behavior in partnership with the Speech team.
• Design for emotional states: Research and design for distinct behavioral and emotional user states — a patient disputing a bill, a dispatcher tracing a late delivery — so the agent adapts seamlessly across happy paths and high-stakes moments.

Skills you’ll bring

• Experience: 5+ years shaping voice user interfaces (VUI), character writing, conversation design, or complex conversational/agentic systems.
• Education: Bachelor's in Linguistics, Communication, Psychology, Design, or equivalent practical experience.
• Prompt fluency: Fluency with LLM-based agent behaviors, prompt engineering, and prompt orchestration — knowing how design choices alter model outputs without relying on code.
• TTS literacy: Working fluency with TTS controls (voice selection, prosodic control) sufficient to set platform standards — the Speech team implements them.
• Portfolio: An exceptional portfolio highlighting voice systems, written persona standards, and interactive logic rather than static flow diagrams.
• Taste: Strong taste and an ear for dialogue — the ability to articulate a character on a page and translate it into consistent AI behavior under pressure.
• Bonus: Experience in regulated, high-stakes verticals (e.g. healthcare, financial services, legal) is a strong plus.

This is a craft/standards role in a product org. If your strength is building production speech systems and models, our AI Engineer, Speech Synthesis (TTS) role is likely the better fit.