Agentic Experience Designer

Safelite; Columbus (OH); On-site; USD 90,000 - 160,000; Full time

Job summary

Safelite in Columbus, OH is seeking a product designer to shape AI-enabled experiences across conversation and multimodal interfaces. You will design end-to-end interactions, balance user control with system autonomy, and collaborate with product and engineering to translate insights into improvements.

The role emphasizes strong Figma proficiency, design systems, and a track record applying AI in the design process to deliver clear, concise, and effective experiences for customers and colleagues.

Qualifications

• Bachelor's Degree or equivalent work experience.
• 4-6 years of product design, interaction design, UX design, conversation design, content design, or related experience.

Responsibilities

• Design end-to-end experiences that allow users to interact with intelligent systems.
• Define how experiences move across conversation, voice, and multimodal interfaces.
• Design how agents interpret intent, gather context, and take action.
• Account for changing intent, incomplete information, interruptions, and exceptions.
• Integrate transparency and explainability into user experiences.

Skills

Product design

UX design

Conversation design

Content design

Figma

Design systems

AI in design

User research

Education

Bachelor's Degree or equivalent

Tools

Figma

AI tools

Design system tooling

Job description

Does this position interest you? You should apply - even if you don't match every single requirement! We're known as an auto glass company. That's the focus of what we do. But beyond the glass, we're so much more. We'll help you build a fulfilling career and encourage you to have a life. Let us be the best place you'll ever work.

A Brief Overview

We are building the next generation of how customers, clients, and colleagues interact with Safelite, with agentic AI creating new possibilities for how people access services, make decisions, and engage with us.

What You Will Do

• Design end-to-end experiences that allow customers, clients, and colleagues to express intent and interact naturally with intelligent systems.
• Define how experiences move across conversation, voice, visual interfaces, structured inputs, and system actions based on the needs of the interaction.
• Design how agents interpret intent, gather context, clarify ambiguity, make recommendations, confirm decisions, take action, and communicate outcomes.
• Account for the complexity of real interactions, including changing intent, incomplete information, interruption, correction, repeat engagement, and exceptions.
• Design beyond the interaction itself, connecting the agent experience to the underlying service, operational process, and outcome.

Design agency, control, and trust

• Establish clear interaction models for what an agent can understand, recommend, decide, and act on.
• Design appropriate levels of customer control based on context, confidence, consequence, and risk.
• Create experiences that communicate uncertainty and limitations clearly without placing the burden of navigating the system on the user.
• Design escalation and human intervention as part of the experience, preserving context and continuity across transitions.
• Integrate transparency, consent, and explainability into the experience in ways that support trust without introducing unnecessary friction.

Define interaction patterns for intelligent experiences

• Establish reusable patterns for agentic, conversational, adaptive, and multimodal experiences across Safelite.
• Explore new interaction models made possible by systems that can interpret context, generate responses, take action, and adapt over time.
• Partner with design system teams to integrate agentic patterns into Safelite's broader experience system.
• Codify principles and patterns as the organization learns, creating a foundation that becomes stronger with each implementation.

AI-Enabled Experience Optimization

• Use AI-native tools to analyze customer interactions at scale, identify patterns, surface emerging issues, and uncover opportunities to improve agent behavior and experience quality.
• Move between patterns across thousands of interactions and individual conversations to understand where intent, agent behavior, and outcomes diverge.
• Use AI to form and investigate hypotheses, identify root causes, and determine where changes to the agent or experience can have the greatest impact.
• Combine conversation intelligence, behavioral data, research, and evaluation to develop a clear point of view on what should change and why.
• Partner with product and engineering to translate those insights into improvements, then evaluate how those changes perform in live interactions.
• Create a continuous feedback loop where AI helps us understand and improve the AI-enabled experiences we put into the world.

Performs other duties as assigned

Complies with all policies and standards

Qualifications

• Bachelor's Degree or equivalent work experience
• 4-6 years of product design, interaction design, UX design, conversation design, content design, or related experience.

Required Skills And Abilities

• 5+ years of product design, interaction design, UX design, conversation design, content design, or related experience.
• Demonstrated experience designing conversational, AI-enabled, adaptive, or intelligent products that have been used in production.
• Strong interaction design capability across conversation, interface, information architecture, and complex service experiences.
• Strong content judgment and the ability to make sophisticated interactions clear, concise, and natural.
• Advanced fluency in Figma and experience contributing to scalable design systems.
• Demonstrated fluency using AI throughout the design process, including discovery, synthesis, exploration, prototyping, evaluation, and optimization.
• Experience using AI-native tools to analyze customer interactions, investigate agent performance, test hypotheses, and identify opportunities for improvement.
• Experience working with agent evaluation, simulation, experimentation, or observability tools to understand how intelligent experiences behave in production.