Conversation Designer, Agent Voice & Personality
- Status
- Open
- Remote policy
- Not stated
- Employment type
- Not stated
- Salary
- Not stated
- Categories
- Engineering
- Tech
- design
- Source
- tripactions
- First observed
- 2026-10-15 09:54 UTC
- Last seen
- 2026-10-15 09:54 UTC
- Source claims posted
- 2026-10-15 08:33 UTC
- Consecutive misses
- 0 of 3
What the posting says
Navan is on a mission to make travel easy for every frequent traveler, and in the process to transform travel and expense management as the world knows it. With over 50 global offices and unicorn status since 2019, Navan has rapidly scaled while disrupting the corporate travel industry.
We’re expanding our Tel Aviv office and looking for a Conversation Designer to join Navan Edge, our new AI-first product built for frequent business travelers. You’ll decide who our agent is: how it sounds, how it thinks out loud, how it handles a delayed flight at 2 a.m., and how it earns a traveler’s trust one message at a time.
If you’re the person who can spot an off-tone sentence instantly, explain exactly why it’s wrong, and rewrite it so it sounds human, this role is for you.
What You’ll Do:
Define our AI agent’s tone of voice, character and personality, and turn them into clear, usable guidelines for the agent and the team.
Test and iterate on the agent’s voice. Build evaluation criteria and test sets, review real conversations, and refine based on what you find.
Write conversational copy across the product, including agent responses, onboarding, prompts and suggestions, errors and edge cases, notifications, and the in-between moments.
Design how the agent behaves when things go wrong: delays, cancellations, misunderstandings, and handoffs to human support.
Keep voice and tone consistent across chat, voice and visual surfaces, from first message to post-trip follow-up.
Partner with Product, Design, Data, and Marketing. Use qualitative feedback and quantitative data to guide your decisions.
Champion user trust and transparency in how the agent communicates, especially around recommendations, decisions and personalization.
Present your work and its rationale clearly to cross-functional partners and senior stakeholders.
Own your work from concept through launch and post-launch iteration.
What We’re Looking For:
5+ years of experience in conversation design, UX writing, content design, or a closely related field.
Native-level English. You have an ear for rhythm, nuance and register, and you know when a sentence sounds slightly off.
Hands-on experience designing for conversational products: chatbots, AI assistants, voice interfaces, or LLM-powered agents.
A portfolio that shows how you developed a voice or personality, and how that voice shows up in real conversational copy and dialogue.
Experience writing for and with LLMs, including prompting, iterating on model output, and judging quality at scale. Alternatively, a strong curiosity about it and a fast learning curve.
Strong analytical skills, with the ability to turn conversation logs and data into concrete improvements.
Excellent collaboration and communication skills across disciplines, especially with engineering and data science.
Bonus Points:
Experience building evaluation frameworks or rubrics for AI output.
A background in creative writing, screenwriting, character writing, or editorial work.
Experience in travel tech, hospitality or logistics, and an understanding of time-sensitive, multi-step journeys.
Experience designing for voice interfaces.
Navan uses AI-assisted Automated Employment Decision Tool (Metaview) to assist with evaluating resumes against job qualifications for this role. All final decisions are made by human recruiters and hiring managers.
Human oversight: Metaview does not automatically reject candidates or make final hiring decisions. Our recruiters and hiring managers review all outputs and make the final hiring decision regarding every application.
Your rights: If you prefer to have your application reviewed without AI assistance, you may request a human evaluation by entering your email here. Your decision to do so will not affect how your candidacy is evaluated.
Please refer to our Candidate Privacy Notice for more information about our processing of personal data, and your rights.
Quality
- x Salary range stated weight 35%
- x Remote policy stated weight 20%
- + Location stated weight 15%
- + Organisation stated weight 15%
- + Publication date stated weight 15%
Not enough history yet to judge honesty signals.
Timeline
-
*
#1359047 2026-10-15 09:54 UTCPublished