Staff Conversational Designer, Voice AI

Socket.dev; San Francisco (CA); On-site; USD 140,000 - 210,000; Full time

Job summary

Deepgram builds the models and APIs that put voice agents into production at scale. You will define how Deepgram's voice agents converse: persona, turn-taking, repair, confirmation, and pacing, working with ML and Engineering on tradeoffs like endpointing and latency budgets.

You will create evals and reference experiences to show developers how to build natural conversations on the Voice Agent API, shaping this discipline at Deepgram and defining what good means for this emerging field.

Qualifications

• Deep experience designing conversational behavior for LLM-based voice agents or assistants, not only scripted IVR flows.
• Fluency with the speech pipeline from ASR through TTS and an understanding of where design decisions live.
• Track record designing turn-taking, interruption, repair, and confirmation patterns that shipped and held up in production.
• Evidence of building quality measurement into the practice: evals, transcript review, benchmarks, or structured failure-analysis loop.
• Exceptional writing craft, including sample dialogs, design guidance, and documentation that others can build against.
• Experience influencing engineering and ML partners on behavior they own, without authority over them.
• Experience designing for developers or technical users, including APIs, SDKs, and documentation surfaces.
• A working AI practice, with a point of view on where these tools help and where they mislead

Responsibilities

• Define the persona and voice system for Deepgram voice agents, and keep it coherent across experiences and use cases.
• Design turn-taking, barge-in, and end-of-turn behavior with ML and Engineering, tuning responsiveness against the risk of interrupting the user, per use case.
• Design conversational repair, no-match and no-input handling, and confirmation strategy, including guardrails that require confirmation before high-stakes actions.
• Own latency-aware pacing and perceived responsiveness: brevity, backchanneling, hold and filler speech, all against real-time budgets.
• Establish conversational-quality evals and a transcript review practice that turns production failures into a repeatable design loop.
• Build the reference agent experiences and developer-facing design guidance that demonstrate best-practice conversation on the Voice Agent API.
• Partner with ML and Research on ASR and TTS behavior, and on the quality criteria that define a good conversation.
• Set the conversation-design principles, review standards, and shared vocabulary the broader team adopts

Skills

Conversational design

LLM-based voice agents

Documentation/writing

APIs & developer docs

Tools

ASR pipeline

TTS pipeline

Voice Agent API

Job description

Deepgram builds the models and APIs that put voice agents into production at scale. You will define how Deepgram's voice agents converse: persona, turn-taking, repair, confirmation, and pacing, working with ML and Engineering on tradeoffs like endpointing and latency budgets.

You will create evals and reference experiences to show developers how to build natural conversations on the Voice Agent API, shaping this discipline at Deepgram and defining what good means for this emerging field.