SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Deepgram is the leading platform for the Voice AI economy, providing real-time APIs for speech-to-text, text-to-speech, and production-grade voice agents at scale. The company has processed over 50,000 years of audio and transcribed more than 1 trillion words, serving 200,000+ developers and 1,300+ organizations including Twilio, Cloudflare, and Jack in the Box.
You will be Deepgram's first Staff Conversational Designer, owning how the company's voice agents converse end-to-end. This is a foundational role defining a discipline that does not yet exist at Deepgram. You will report directly to the Director of Product Design and create leverage for the broader organization through patterns, guidance, and reference experiences.
Key responsibilities include:
- Define persona and voice system for Deepgram voice agents, maintaining coherence across experiences and use cases
- Design turn-taking, barge-in, and end-of-turn behavior in collaboration with ML and Engineering, balancing responsiveness against interruption risk
- Design conversational repair, no-match/no-input handling, and confirmation strategies, including guardrails for high-stakes actions
- Own latency-aware pacing and perceived responsiveness: brevity, backchanneling, hold and filler speech within real-time budgets
- Establish conversational-quality evals and transcript review practices that turn production failures into repeatable design loops
- Build reference agent experiences and developer-facing design guidance demonstrating best-practice conversation on the Voice Agent API
- Partner with ML and Research on ASR and TTS behavior and quality criteria for good conversation
- Set conversation-design principles, review standards, and shared vocabulary the team adopts
You will thrive in this role if you believe conversation is a craft with real depth, get energized by foundational work defining what good means, and think the fastest way to raise quality is to make it measurable then repeatable. The company operates with an AI-first mindset and moves at the pace of AI—change is rapid and you should expect your day-to-day work to evolve quickly.
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, with working understanding of where design decisions live inside it
- Track record designing turn-taking, interruption, repair, and confirmation patterns that shipped and held up in production
- Evidence of building quality measurement into practice: evals, transcript review, benchmarks, or structured failure-analysis loop
- Exceptional writing craft, including sample dialogs, design guidance, and documentation others can build against
- Experience influencing engineering and ML partners on behavior they own without direct authority
- Experience designing for developers or technical users, including APIs, SDKs, and documentation surfaces
- Working AI practice with a point of view on where these tools help and where they mislead
NICE-TO-HAVE:
- Time on a named assistant or 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
