Deepgram
Staff Conversational Designer
$180K–$240K
San Francisco, CA · Remote · Staff · Full-time · Posted Sep 19, 2026
- Experience
- No specific years stated; expertise and leadership matter more than years of experience.
About the job
Defines and ships the conversational behavior, quality measures, and developer guidance for Deepgram’s voice agents in partnership with ML and Engineering.
What you'll do
- Define voice-agent persona, turn-taking, interruption, repair, confirmation, and latency-aware pacing.
- Create conversational-quality evaluations and transcript-review practices to improve production behavior.
- Build reference agent experiences and developer-facing guidance for the Voice Agent API.
What they ask for
- Deep experience designing conversational behavior for LLM-based voice agents or assistants.
- Fluency with the speech pipeline from ASR through LLM to TTS, and understanding of where design decisions occur.
- Track record shipping production turn-taking, interruption, repair, and confirmation patterns; experience measuring quality through evals, reviews, benchmarks, or failure analysis.
- Exceptional writing craft; ability to influence Engineering and ML partners; experience designing for developers or technical users; working AI practice.
Nice to have
- Experience with a named assistant or production voice-agent platform, Wizard of Oz testing, sample dialogs, or LLM/voice eval tooling.
- Experience in high-stakes or regulated domains, multilingual or cross-locale conversation design, or high-growth B2B companies.
Pay
$180K – $240K USD base salary
Tools
Voice Agent API, ASR, LLM, TTS, APIs, SDKs
AI focus
Designs LLM-based voice-agent behavior and quality evaluation; expected to actively use and experiment with advanced AI tools in everyday work.
Model-written summary · the original posting is authoritative