Staff Voice AI Conversation Designer

AI Chopping Block; San Francisco, Northern (CA, KY); On-site; USD 150,000 - 190,000; Full time

Job summary

Deepgram is hiring a Staff Conversational Designer to define how voice agents converse—persona, turn-taking, repair, confirmation, and pacing. You’ll work with ML and Engineering on tradeoffs like endpointing and latency budgets, and you will build evaluation methods and reference experiences for developers using the Voice Agent API.

This is a foundational, category-creating role where your patterns and guidance shape product design across the organization.

Qualifications

• Design conversational behavior for LLM-based voice agents, not just scripted flows.
• Fluency with the speech pipeline from ASR through LLM to TTS.
• A track record designing turn-taking, interruption, repair, and confirmation patterns.
• Evidence of building quality measurement into practice (evals, transcripts).
• Exceptional writing craft with dialogs, guidance, and documentation.

Responsibilities

• Define the persona and voice system for Deepgram voice agents, and keep it coherent across experiences.
• Design turn-taking, barge-in, and end-of-turn behavior with ML and Engineering.
• Design conversational repair, no-match and no-input handling, and confirmation strategies.
• Own latency-aware pacing and perceived responsiveness against real-time budgets.
• Establish conversational-quality evals and a transcript review practice.
• Build reference agent experiences and developer-facing design guidance.
• Partner with ML and Research on ASR and TTS behavior and quality criteria.
• Set conversation-design principles, review standards, and shared vocabulary.

Skills

Conversational design

Voice agents

LLM-based systems

Real-time latency awareness

Job description

Deepgram is hiring a Staff Conversational Designer to define how voice agents converse—persona, turn-taking, repair, confirmation, and pacing. You’ll work with ML and Engineering on tradeoffs like endpointing and latency budgets, and you will build evaluation methods and reference experiences for developers using the Voice Agent API.

This is a foundational, category-creating role where your patterns and guidance shape product design across the organization.