Staff Conversational Designer (PST)

Deepgram•San Francisco, CA

6h•$180,000 - $240,000•Remote

About The Position

Deepgram builds the models and APIs that put voice agents into production at scale. This role is responsible for defining how Deepgram's voice agents converse, including persona, turn-taking, repair, confirmation, and pacing. The designer will collaborate with ML and Engineering on tradeoffs related to endpointing, barge-in, and latency budgets. They will also build evaluations to measure conversational quality and create guidance and reference experiences for developers using the Voice Agent API. This is a foundational role where the individual will define the conversational design discipline at Deepgram. The role reports to the Director of Product Design and is a Staff Individual Contributor (IC) role, focusing on creating leverage for others through patterns and guidance. Key initial responsibilities include developing a documented persona and voice system, and designing and shipping turn-taking and repair behavior with Engineering. Future scope will expand to conversational-quality evaluations and developer-facing guidance.

Requirements

Deep experience designing conversational behavior for LLM-based voice agents or assistants, not only scripted IVR flows
Real fluency with the speech pipeline, from ASR through LLM to TTS, and a working understanding of where design decisions actually live inside it
A 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 a 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

Nice To Haves

Time on a named assistant or a production voice agent platform
Practice with Wizard of Oz testing and sample dialog methods
Hands-on work with eval tooling for LLM or voice quality
Experience in high-stakes or regulated conversation domains where confirmation and recovery carry real cost
Multilingual or cross-locale conversation design experience
Background in high-growth B2B companies with both self-serve and enterprise motions

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