Hiring nowConversation, prompt and context design

Conversation Designer

Also called Conversational AI Designer

A Conversation Designer shapes how an AI service talks, asks, hands over and recovers. They turn model behaviour into dialogue people can finish tasks with, which cuts failed conversations and avoidable escalations.

What they do

They map what users are trying to do, then design the dialogue around it: openings, questions, confirmations, handovers to a person and recovery when the model or the user gets it wrong. They write prompts and context that hold the model to that design. They build dialogue prototypes, run them with real users and revise. They keep prompt versions tidy, build evaluation sets from failed conversations and work with engineers, product and support on what the service should and should not attempt. Tone and wording matter, but structure matters more.

What a strong hire delivers

In the first months, a strong hire leaves behind a clear conversation specification for one live service, covering flows, escalation rules and recovery paths. They add a user-tested dialogue set the team can reuse. They set up an evaluation suite tied to task success. Engineers and support staff can then see what good looks like and spot regressions when prompts or models change.

How you can tell they are good

Ask for a conversation they designed and what happened when real users tried it. Strong candidates show the flow, the failures they found and what they changed. They explain how they measured task success and recovery, not just tone. They can say when the model should stop and hand over. Be wary of portfolios that show only polished scripts and no testing.

Why it is hard to fill

The title is used loosely. Some people with it write chatbot scripts for fixed flows. Others work with open-ended model behaviour, prompts and evaluation. Few have done both. Backgrounds are mixed: linguistics, content design, service design and application design all feed in. Candidates who have shipped and measured a live AI service are scarce, and the best often sit under other titles.

Where to find them

Look at conversation designers from contact centre, banking, telecoms and retail teams that built assistants. Content designers and UX writers who moved into prompt work are strong sources. So are linguists who worked on speech or language products, and service designers from digital teams. Product-led AI companies and voice assistant teams are also worth checking. Titles may read prompt designer, content designer or UX writer.

Indicative pay

Not enough published evidence yet to give a fair range for this role, which is common for work this new. We benchmark it for you as part of a search.

Interview questions for a Conversation Designer

  1. Walk me through a conversation flow you designed. How did you decide where it should escalate to a person?

    Strong answers name concrete triggers such as repeated misunderstanding, high-risk requests or user frustration, and show the cost of both over- and under-escalating. Worry if escalation was an afterthought or left to the model to decide.

  2. Tell me about a dialogue that tested well in the office but failed with real users. What did you change?

    Look for honest account of the gap, the evidence used to find it and a specific revision. A good answer shows learning from user testing. Worry about blaming users or never having tested outside the team.

4 more questions, with what a strong answer covers, are in the Role Kit.

Job description you can post

We are building AI services that people use to get real tasks done. We need a Conversation Designer to shape how those services talk, ask, hand over and recover. You will work with engineers, product and support to turn model behaviour into dialogue that works.

What you will do

  • Design dialogue flows, escalation rules and recovery paths for our AI services
  • Write and version prompts and context that keep model behaviour within the design
  • Build dialogue prototypes and test them with real users
  • Create evaluation sets from failed conversations and track task success
  • Write conversation specifications that engineers and support teams can use
  • Review transcripts regularly and turn findings into design changes

What you will bring

  • Shipped conversation design work that real users have used
  • Examples of user testing and the changes it led to
  • Experience writing and testing prompts or comparable model instructions
  • Clear approach to measuring task success and recovery
  • Ability to explain design choices to engineers and non-specialists
  • Strong writing, with attention to structure as well as wording

Nice to have

  • Background in linguistics or localisation
  • Experience with voice or multilingual services
  • Familiarity with evaluation suites for model outputs

Free to use and adapt. If it saves you time, a link back to this page is appreciated.

Skills that matter

  • Service and conversation designAdvancedStructure dialogue, escalation and service experiences
  • Prompt and context designAdvancedStructure instructions, examples and context for a task
  • Model evaluationWorkingMeasure capability and failure modes credibly
  • Linguistics and localisationWorkingAdapt language behaviour across cultural and linguistic contexts

Other roles in conversation, prompt and context design

Related roles in other families

How we wrote this

Role definitions are our own editorial work, checked against occupational classifications, standards, research and employer pages. Titles vary by company, and this is a description of the work, not a job advert.

← Conversation, prompt and context designAll new job families

Start a search

Hiring a Conversation Designer?

Tell us the work. We find the people already doing it, whatever their job title says, and you meet them already interviewed for your role.