Conversation Designer, HCI

About A1 There are over 5 billion users using basic applications today such email, notes, tasks that are not AI-native. Our mission is to build a proactive smart assistant for everyday users to bring intelligence to conversations, errands, organising and workflows, with minimal prompting. 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. Our objective is to help users complete tasks daily enjoyable with over ~90%* reduced time. 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