Human-Centered Designer

Booz Allen Hamilton•Usa, DC

3d•Remote

About The Position

We are looking for a human-centered designer to own the end-to-end experience of ARPA-H’s production AI assistant G RACE, including how users understand it, trust it, and get real work done with it. Designing for agentic AI is hard, output is probabilistic, workflows are open-ended, and trust is earned interaction by interaction. You will shape how G RACE feels, while operating within the privacy, security, and responsible-use requirements of our mission and the federal environment.

Requirements

7+ years of experience in a product design or UX design field, displaying a portfolio of shipped products
Experience designing for AI, LLM, chat, or agentic products, including streaming responses, citation and source display, tool-call visibility, and for uncertain or probabilistic output
Experience across the full design process, including research, interaction design, and visual or UI design
Experience with modern design tools such as Figma, including components, prototyping, and design systems
Experience planning and running interviews and usability tests, and turning findings into decisions
Experience shipping complex, interactive products in high-velocity environments where you owned the experience end-to-end
Knowledge of industry best practices and design patterns specific to agentic AI, including agent transparency, controllability, human-in-the-loop, and multi-agent workflows
Ability to pay strict attention to detail with a high bar for quality and commitment to accessibility, including WCAG or Section 508
Ability to be a self-starter and clear communicator who works with a high sense of urgency, gives and receives feedback well, works closely with engineers, and makes the people around them better
Bachelor's degree

Nice To Haves

Experience working closely with implementation, including reading the front-end, comprehending what React and Chainlit make easy or hard, and designing within real constraints
Experience building or contributing to design systems at scale
Experience designing productivity tools, research tools, or other complex information-dense products
Experience in startup or early-stage environments
Ability to be comfortable with ambiguity, rapid iteration, and wearing multiple hats
Possession of strong interaction and visual design skills

Responsibilities

Own the design of G RACE across research, interaction, and visual design, being accountable for whether the experience works for users.
Design interaction patterns for agentic AI, including conversational flows, tool-call and reasoning visibility, human-in-the-loop confirmations, error and uncertainty states, and graceful handling of partial or long-running responses.
Design how G RACE presents rich output legibly and trustworthily, including citations, tables, diagrams, maps, generated images, and long-form results.
Bring and apply industry best practices and emerging design patterns specific to agentic AI, including agent transparency, controllability, memory and context, multi-agent workflows, and letting users build and direct their own agents.
Create the flows, wireframes, prototypes, and high-fidelity designs that turn ambiguous problems into shippable interfaces.
Own and evolve a design system so the product stays consistent, accessible, and fast to extend.
Talk to ARPA-H users and comprehend their workflows, goals, and where G RACE helps or gets in the way.
Run lightweight, high-velocity research through interviews, usability tests, and concept validation that fit a team that ships weekly, not quarterly.
Turn research into clear, prioritized insights that the team can act on, and close the loop by measuring whether changes helped.
Build a durable understanding of who G RACE serves and advocate for them in every decision.
Design for trust as a first-class outcome.
Design for the realities of AI, including hallucination, uncertainty, latency, and failure.
Ensure accessibility is designed in from the start.
Bring genuine care for the sensitivity of the mission.
Work hand-in-hand with engineers, the applied researcher, and product to translate design intent into shipped product, including closely with front-end so fidelity and interaction detail survive to production.
Prototype quickly, get it in front of users, and iterate.
Communicate design decisions clearly to both designers and non-designers, and make the rationale, not just the mockup, legible to the team.