Conversation Designer, HCI

Bjak; New York (NY); On-site; USD 80,000 - 120,000; Full time

Job summary

Bjak seeks a skilled conversation designer to create engaging AI communication for users. This role focuses on designing conversational flows, setting expectations, and defining how the AI interacts across tasks and workflows.

Ideal candidates have experience in conversation design and a solid understanding of AI product interactions. The position is crucial for creating trust, clarity, and effective user assistance.

Qualifications

• Experience in conversation design, UX writing, interaction design, or related field.
• Strong understanding of conversational UX for AI products.
• Ability to design multi-turn interactions and error recovery.
• Clear thinking about trust and AI limitations.

Responsibilities

• Design conversational flows for AI interactions and task completion.
• Define AI expectations, uncertainty signals, and input requests.
• Develop prompts, response templates, and behaviors for tasks.
• Analyze conversation logs for failure points and recovery gaps.
• Build and maintain conversation design standards.

Skills

Experience in conversation design

Strong understanding of conversational UX

Ability to design multi-turn interactions

Clear thinking about AI communication

Collaborating with engineers and product managers

Attention to language and tone

Job description

Company

A1 is building a proactive AI smart assistant for everyday users to bring intelligence to conversations, errands, organising and workflows.

Our product focuses on achieving high reliability for long-running workflows, persistent context, and real-world task completion. The system must handle multi-step reasoning, interact with external tools, and remain reliable despite non-deterministic model behavior.

Role

You will design how the AI communicates with users - what it says, when it says it, how it asks for clarification, how it explains actions, and how it handles mistakes.

This role is central to HCI. The assistant must communicate clearly, set expectations, ask for the right input, explain uncertainty, and help users stay in control across long-running workflows.

There are no established frameworks for this kind of AI conversation design at the level of reliability and context depth we are building. You will help define them.

What You'll Be Doing

• Design conversational flows for AI interactions across chat, task completion, and assistant-guided workflows.

• Define how the AI sets expectations, signals uncertainty, asks for input, and communicates errors or limitations.

• Develop prompts, response templates, fallback patterns, and assistant behaviors for multi-step and long-running tasks.

• Design how users supervise, interrupt, correct, and redirect AI behavior through conversation.

• Design for trust and transparency without overwhelming users with unnecessary detail.

• Work with product, engineering, and ML teams to define how the assistant handles ambiguity, memory, and context across sessions.

• Analyze conversation logs to identify failure points, misaligned expectations, and recovery gaps.

• Define tone, voice, and response principles across different user needs and product surfaces.

• Build and maintain conversation design standards and pattern libraries.

What You Will Need

• Experience in conversation design, UX writing, interaction design, or a related field.

• Strong understanding of conversational UX for AI products, chatbots, voice assistants, or assistant-led workflows.

• Ability to design multi-turn interactions, including prompting flows, error recovery, clarification, and context handoff.

• Clear thinking about how AI systems should communicate trust, limitations, progress, and failure.

• Experience collaborating with engineers, product managers, and ML teams.

• Comfort working with evolving product requirements and non-deterministic system behavior.

• Strong attention to language, tone, clarity, and how words land in context.

• Ability to think about long conversation arcs, user intent over time, and memory-aware interactions.