Remote Lead Voice AI Conversation Designer

Socket.dev; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Deepgram is hiring a Staff Conversational Designer to define how our voice agents converse, including persona, turn-taking, repair, and pacing. You will collaborate with ML and Engineering to optimize endpointing, barge-in, and latency budgets while building measurable standards for conversational quality.

You will develop reference experiences and guidance for developers, ensuring our Voice Agent API enables natural, reliable conversations at scale.

Qualifications

• Expertise designing conversational behavior for LLM-based voice agents or assistants, not just scripted flows.
• Ability to work with ML/Engineering on behavior tradeoffs (endpointing, latency budgets).
• Experience building quality measurement into practice: evals, transcript review, benchmarks.

Responsibilities

• Define persona and voice system for Deepgram voice agents.
• Design turn-taking, barge-in, end-of-turn behavior with ML and Engineering.
• Design repair, no-match/no-input handling and confirmation patterns.
• Own latency-aware pacing and perceived responsiveness against real-time budgets.
• Establish conversational-quality evals and a transcript review practice.

Skills

Conversational design

LLM-based voice agents

Developer-facing guidance

Documentation for API/SDKs

Job description

Deepgram is hiring a Staff Conversational Designer to define how our voice agents converse, including persona, turn-taking, repair, and pacing. You will collaborate with ML and Engineering to optimize endpointing, barge-in, and latency budgets while building measurable standards for conversational quality.

You will develop reference experiences and guidance for developers, ensuring our Voice Agent API enables natural, reliable conversations at scale.