Remote Staff Conversational Designer, Voice AI

Design Better Podcast; San Francisco (CA); À distance; USD 150 000 - 230 000; Plein temps

Résumé du poste

Deepgram is hiring a Staff Conversational Designer to define how voice agents converse—persona, turn-taking, repair, confirmation, and pacing. You will work with ML and Engineering to align behavior with endpointing, latency budgets, and production realities.

You will build evaluative frameworks and reference experiences to guide developers and ship scalable patterns for the Voice Agent API, setting a disciplined practice for the fledgling design area.

Qualifications

• Proven ability to design conversational behavior for voice agents.
• Experience with turn-taking, interruption handling, and repair patterns.
• Strong writing craft with sample dialogs and design docs.
• Experience influencing engineering/ML partners without authority.
• Ability to define benchmarks and evaluative guidance for production deployments.

Responsabilités

• Define persona and voice system consistency across Deepgram experiences.
• Design turn-taking, barge-in, end-of-turn behavior in collaboration with ML/Engineering.
• Develop repair, no-match, and confirmation strategies, with guardrails for high-stakes actions.
• Own latency-aware pacing and perceived responsiveness within real-time budgets.
• Establish conversational-quality evals and a transcript review process.
• Create reference agent experiences and developer-facing design guidance for the Voice Agent API.
• Collaborate with ML and Research on ASR/TTS behavior and quality criteria.
• Set design principles, review standards, and shared vocabulary for the team.

Connaissances

Conversational design

LLM-based voice agents

Speech pipeline knowledge

Writing craft

Engagement with ML/Engineering

Developer-facing guidance

Description du poste

Deepgram is hiring a Staff Conversational Designer to define how voice agents converse—persona, turn-taking, repair, confirmation, and pacing. You will work with ML and Engineering to align behavior with endpointing, latency budgets, and production realities.

You will build evaluative frameworks and reference experiences to guide developers and ship scalable patterns for the Voice Agent API, setting a disciplined practice for the fledgling design area.