Remote Staff Conversational Designer, Voice AI Systems

Apply; San Francisco, Northern (CA, KY); Hybrid; USD 140,000 - 200,000; Full time

Job summary

Deepgram builds 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. You will work directly with ML and Engineering on endpointing, barge-in, and latency budgets.

You will build the evals that measure conversation quality for developers using the Voice Agent API. This is a leading edge Staff IC role, reporting to the Director of Product Design, with broad leverage across

Qualifications

• Experience designing conversational behavior for voice agents or assistants.
• Strong understanding of ASR through TTS in a production setting.
• Track record shipping turn-taking, interruption, repair and confirmation patterns.

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 interrupt risk per use case
• Design conversational repair, no-match and no-input handling, and confirmation strategy with guardrails
• Own latency-aware pacing and perceived responsiveness: brevity, backchanneling, hold and filler speech against real-time budgets
• Establish conversational-quality evals and a transcript review practice for production failures
• Build the reference agent experiences and developer-facing design guidance for best-practice conversations
• Partner with ML and Research on ASR and TTS behavior and quality criteria for good conversations
• Set design principles, review standards, and shared vocabulary adopted by the team

Skills

Conversational design

Voice agent design

LLM-based systems

Multilingual design

Technical writing

Job description

Deepgram builds 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. You will work directly with ML and Engineering on endpointing, barge-in, and latency budgets.

You will build the evals that measure conversation quality for developers using the Voice Agent API. This is a leading edge Staff IC role, reporting to the Director of Product Design, with broad leverage across