Human Centered Designer (#26-119)-Washington,District of Columbia

Strategic Analysis, Inc. (SA) Is seeking a Human Centered Designer for the Advanced Research Projects Agency for Health (ARPA-H) Overview: GRACE is ARPA-H's production AI assistant. We've shipped the first generation of agentic AI, and now we're moving quickly to go deeper: user-built agents, multi-agent orchestration, and a platform teams can extend themselves. We are a small, startup-minded team that ships fast and owns what we build end-to-end. We are looking for a senior front-end-leaning full-stack developer to own the experience layer of GRACE: the chat interface, the rich rendering of AI output, and the interaction patterns that make an agentic system feel trustworthy and fast. The front end is where users decide whether GRACE is reliable and worth using. You will own that surface, while operating within the privacy, security, and responsible-use requirements of our mission and the federal environment. Responsibilities: Own the Experience End-to-End • Own the design of GRACE across research, interaction, and visual design; you are the person accountable for whether the experience actually works for users • Design interaction patterns for agentic AI: 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 GRACE presents rich output legibly and trustworthily: citations, tables, diagrams, maps, generated images, and long-form results • Bring and apply industry best practices and emerging design patterns specific to agentic AI: 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 Do the Research • Talk to ARPA-H users; understand their workflows, their goals, and where GRACE helps or gets in the way • Run lightweight, high-velocity research: interviews, usability tests, and concept validation that fit a team that ships weekly, not quarterly • Turn research into clear, prioritized insights the team can act on, and close the loop by measuring whether changes actually helped • Build a durable understanding of who GRACE serves and advocate for them in every decision Design for Trust and Responsibility Work hand-in-hand with engineers, the applied researcher, and product to translate design intent into shipped product; partner especially closely with front-end so fidelity and interaction detail survive to production Requirements: • 7 years of professional experience in product design, UX design, or a closely related field, with a strong portfolio of shipped products • Experience designing for AI, LLM, chat, or agentic products: streaming responses, citation and source display, tool-call visibility, and designing for uncertain or probabilistic output • Working knowledge of industry best practices and design patterns specific to agentic AI (agent transparency, controllability, human-in-the-loop, multi-agent workflows) • Demonstrated ownership across the full design process: research, interaction design, and visual/UI design • Strong interaction and visual design skills, with fluency in a modern design tool (e.g., Figma) including components, prototyping, and design systems • Hands-on user research experience: planning and running interviews and usability tests, and turning findings into decisions • Proven experience shipping complex, interactive products in high-velocity environments where you owned the experience end-to-end • Strong commitment to accessibility (WCAG / Section 508) • Strong attention to detail and a high bar for quality; you care about how it looks, how it feels, and how it holds up in real use • Clear communicator who gives and receives feedback well, works closely with engineers, and makes the people around them better • Self-starter with a high bar and a high sense of urgency; you do not wait for perfectly scoped problems Preferred Qualifications • Comfort working close to implementation: reading the front end, understanding 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 • Track record in startup or early-stage environments: comfort with ambiguity, rapid iteration, and wearing multiple hats experience Location: Remote Clearance: Ability to obtain HHS Public Trust.
Strategic Analysis, Inc. is an Equal Opportunity employer and is committed to non-discrimination in employment. All qualified applicants will receive consideration for employment without regard to race, color, religions, sex (including pregnancy, sexual orientation, or gender identity), national origin, disability (physical or mental), age (40 or older), protected veteran status, genetic information (including family medical history) or any other characteristic protected by law. This policy includes but is not limited to the following employment actions: recruitment, hiring, firing, promotion, demotion, compensation, fringe benefits, training, mentoring and sponsorship programs.