Staff AI Product Designer

Intercom is the AI Customer Service company on a mission to help businesses provide incredible customer experiences.

Our AI agent Fin, the most advanced customer service AI agent on the market, lets businesses deliver always-on, impeccable customer service and ultimately transform their customer experiences for the better. Fin can also be combined with our Helpdesk to become a complete solution called the Intercom Customer Service Suite, which provides AI enhanced support for the more complex or high touch queries that require a human agent.

Founded in 2011 and trusted by nearly 30,000 global businesses, Intercom is setting the new standard for customer service. Driven by our core values, we push boundaries, build with speed and intensity, and consistently deliver incredible value to our customers.

Role Overview

We’re looking for a Staff AI Product Designer to shape what our AI does, how it behaves, and how it fits into real user workflows.

This role sits at the intersection of product, design, and machine learning—turning emerging capabilities into reliable, high-quality user experiences. You’ll design systems: behaviors, decisions, orchestration, and end-to-end experiences powered by AI.

This is not a traditional product design role. You’ll go beyond interface design to define how AI systems behave, operate, and deliver value in the real world—similar to emerging “AI Model Designer” roles, but more deeply embedded in product.

What You’ll Do

1. Define AI capabilities (the “what and why”)

Identify and pattern match high-value opportunities for AI across the product

Define what AI should do—and just as importantly, what it should not do, making hard or unpopular calls when needed

Set clear boundaries for autonomy vs human control

2. Design AI behavior, orchestration, and system logic

Architect AI-driven workflows and agentic systems that operate across real-world scenarios and over time, including multi-step and agent-to-agent interactions

Establish decision frameworks: when systems should act, ask, escalate, or defer

Design for uncertainty, failures, and edge cases as core system behavior

Develop and apply design principles and heuristics to shape how AI systems behave and make decisions

Ensure systems remain coherent and predictable, even as complexity scales

3. Shape human + AI workflows and end-to-end experience

Design experiences for users who are increasingly managing AI systems and agents

Design how AI integrates into real user workflows, not just isolated interactions

Define the role of the human in the loop: where users guide, review, or override

Ensure users can understand, trust, and recover from system failures

Partner with product designers to continuously shape and adapt the product experience as underlying systems evolve

4. Define quality, evaluation, and reliability

Define what “good” looks like (e.g. trust, accuracy, effort reduction, and whether outputs are structured and usable in context)

Design evaluation scenarios and feedback loops

Analyse outputs to identify failure modes and system weaknesses

Design for reliability at the system level, preventing agentic breakdowns

How You’ll Work

Shape direction from the earliest stages of zero-to-one problems

Influence across teams without formal authority

Operate in a highly autonomous, fast-moving environment with evolving constraints

Lead ambiguous, in-flight work—making calls on when to adapt the product vs. push on system improvements as things evolve

Act as a bridge between AI research, technical capabilities, and user needs

Collaborate deeply with ML scientists, PMs, and product designers

Prototype and run focused experiments that isolate variables and generate clear insights

Stay close to system behaviour by regularly reviewing outputs and raising the bar on quality

What We’re Looking For

Strong product judgment—you consistently make high-quality calls on what to build and why

Ability to influence without authority

Ex