AI Experience Engineer

Title:   AI Experience Engineer (P4) 

Location:  Remote – USA, Canada, Europe or Australia 

Reports to:  Sr. Director, AI & Innovation 

Vacancy: New - Internal Posting 

The Role:    

AI Experience Engineer is a full-stack role. You are not a frontend engineer with design instincts and you are not a UX designer who codes. You are an engineer who owns the complete human-facing layer of AI-powered systems from data model through backend service through polished, production-quality interface. On the Innovation Crew, that means designing and building the interactions that make agentic AI capabilities legible, trustworthy, and useful to engineers, analysts, and business stakeholders. Your observability standard is not a human approval gate on every agent output. It is an inspectable, traceable system where humans can assess the process as needed, surface what matters when it matters, and course-correct without being in the critical path of every step. In your first 30 days, you will have audited the team's current design system and shipped your first agent interaction component. By day 60, you will have a working observability interface that lets the team review agent traces without engineering intervention. By day 90, the design system foundations are documented and available to Launch Lab for production consumption. 

How we Build Agents: 

The Innovation Crew is actively forming its own AI agent workforce to accelerate delivery. As AI Experience Engineer, your contribution to that workforce is the observability and interaction layer: the interfaces that let engineers review agent traces, inspect outputs, and course-correct when needed without becoming bottlenecks in every agent cycle. You bring the "human on the loop" standard to life: observable systems where a person can assess what happened and intervene when it matters, rather than approve every step. When a pattern for AI interaction or agent observability works, you document it as a reusable component and share it with the engineering organization. 

The Impact You Will Have in This Role:   

The interfaces you build are often the first thing a business executive or engineering director sees when the Innovation Crew presents a new capability. Your work determines whether a technically sophisticated system lands as a compelling, trustworthy vision or a confusing demo. Beyond individual demos, the interaction patterns and component library you define will shape how JD Power's AI Assistants and Copilots capability pillar is experienced across the organization. The observability interfaces you design for the team's agent workforce will become the model for how humans stay informed about and in control of autonomous systems at JD Power. 

What You’ll Be Doing in This Role:  

• Own the full-stack design and engineering quality for all Innovation Crew pilots and prototypes: take concepts from brief or wireframe through backend service, API integration, and polished production-quality interface; ensure every deliverable shown to engineering leadership or business stakeholders is visually consistent, accessible, and immediately legible to non-technical audiences. 

• Design the human-on-the-loop interaction patterns for agentic systems: build the interfaces that let engineers and reviewers inspect agent traces, audit reasoning outputs, adjust parameters, and surface anomalies, with the goal of keeping humans informed and in control without making them a bottleneck at every step. The standard is observable by default, not approved at every gate. 

• Build and maintain a shared design system and component library for Innovation Crew outputs, including AI-specific components: streaming output displays, agent status and progress indicators, trace inspection views, confidence surfaces, and human-review interfaces that Launch Lab can consume directly when taking pilots to production. 

• Define the UX standards and interaction vocabulary for the AI Assistants and Copilots capability pillar: contextual AI assistance interfaces, real-time knowledge retrieval surfaces, AI-generated content displays, and role-specific intelligence dashboards - establishing the patterns JD Power will use as these capabilities scale. 

• Conduct lightweight user research and usability testing with internal stakeholders and business unit partners; bring user signal into the Innovation Crew design process early enough to shape what gets built, not just how it looks; partner with the Principal AI Engineer to design evaluation interfaces and agent observability dashboards that make model behavior and trace output readable for human reviewers. 

• Champion WCAG accessibility standards and performance engineering across all Innovation Crew deliverables; apply JD Power brand guidelines to any output shown externally; contribute UX and frontend technology evaluations to the Emerging Technology Radar process and propose directional Architecture Decision Records for AI interaction patterns the Innovation Crew adopts. 

Qualifications of this Role:  

• Full-stack engineering with frontend depth: you can build backend services, wire up data sources, and produce a polished production-quality interface in the same sprint. 

• Production experience with AI-powered systems: you have shipped something with streaming output, agent interaction surfaces, human-review workflows, trace inspection interfaces, or similar, and you understand that LLM systems are non-deterministic and must be designed to allow for regular inspection from the start. 

• React (or equivalent) and modern design systems with the ability to design the interaction AND implement it; you move fluidly between designing in Figma and building in code without the handoff friction that slows most teams down. 

Also Valued 

• Experience with agent observability tooling (Langfuse, LangSmith, Phoenix/Arize, or equivalent) and the ability to design interfaces that make trace data useful to non-engineers. 

• Data visualization for non-technical audiences; WCAG accessibility standards; JD Power product ecosystem or user base familiarity. 

• Eval harness design or familiarity with LLM-as-judge patterns understanding what "quality" means for an agentic system informs better inspection interfaces. 

• Strong product intuition: you ask "what does the user actually need from this agent?" before deciding how to surface it. 

The Hiring Manager says:   

“I am looking for an intuitive mind who understands that the interface is not decoration, it is how trust gets built or lost. You know that "the AI worked in the demo" is not a production standard. You design systems where humans can see what happened, understand why, and intervene when needed without sitting in every decision loop. The work you ship here will be shown to executives and potentially external clients. Your name is on it.” 

This position has a starting salary range of $130,000 - $160,000 USD / $115,000 - $130,000 CAD per year. This is the range we reasonably and in good faith expect to pay for the role at the time of posting. An employee’s pay within the range is determined by a number of factors, including relevant skills, education, qualifications, experience, performance, business or organizational needs, and geographic location. 

Our Values 
We POWER Our Customer’s Success