Staff Conversational Designer (PST)

Deepgram
San Francisco
Workplace: RemoteFull timeUSD 180,000 - 240,000 annuallyFunction: Design (Product/UX/UI/Visual)Skills: ["Leadership","Writing craft","Influence","Quality measurement"]

Own end-to-end conversational design for voice agents, defining persona, turn-taking, repair, confirmation, and pacing across experiences. Partner with ML and Engineering to tune real-time behaviors like endpointing, barge-in, and latency-aware responsiveness. Build conversational-quality evals and transcript review practices, and publish developer-facing reference experiences and design guidance for the Voice Agent API. Help establish the discipline at Deepgram.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Deepgram
Deepgram
1 day ago

Staff Conversational Designer (PST)

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 5 hours agoStatus: Live

Job Summary

Own end-to-end conversational design for voice agents, defining persona, turn-taking, repair, confirmation, and pacing across experiences. Partner with ML and Engineering to tune real-time behaviors like endpointing, barge-in, and latency-aware responsiveness. Build conversational-quality evals and transcript review practices, and publish developer-facing reference experiences and design guidance for the Voice Agent API. Help establish the discipline at Deepgram.
Location: San Francisco
Workplace: Remote
Employment Type: Full time
Job Function: Design (Product/UX/UI/Visual)
Seniority: Mid level

Key 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 per use case.
  • •Design conversational repair, no-match/no-input handling, and confirmation strategy with guardrails for high-stakes actions.
  • •Own latency-aware pacing and perceived responsiveness (brevity, backchanneling, hold/filler speech) against real-time budgets.
  • •Establish conversational-quality evals and transcript review, then build reference agent experiences and developer-facing guidance.

Pay and Benefits

Salary: USD 180,000 - 240,000 annually
Equity and Bonus:Equity

Key Requirements

  • •Deep experience designing conversational behavior for LLM-based voice agents or assistants, beyond scripted IVR flows.
  • •Fluency across the speech pipeline (ASR through LLM to TTS) and understanding where design decisions live.
  • •Track record shipping turn-taking, interruption, repair, and confirmation patterns that held up in production.
  • •Experience building quality measurement into the practice via evals, transcript review, benchmarks, or failure-analysis loops.
  • •Exceptional writing craft to produce sample dialogs and documentation others can build from.
Skills:LeadershipWriting craftInfluenceQuality measurement
Tech Stack:LLMASRTTSVoice Agent APIAPIsSDKsEvalsTranscript review

Company Brief

Deepgram
Deepgram builds a real-time Voice AI platform delivering speech-to-text, text-to-speech, and voice-agent APIs for developers and enterprises, focusing on low-latency, high-accuracy voice models and scalable deployment options.
Industry: API Platforms
Company Size: Medium (51 to 250 employees)
Growth: Scaleup
Valuation: Unicorn (USD 1B+)
Funding: Series C
Headquarters: San Francisco, United States
Founded: 2015
Glassdoor
Glassdoor: 4.5
WebsiteLinkedInGlassdoor