Sr Staff, AI Engineer

What if the work you did every day could impact the lives of people you know? Or all of humanity?

At Illumina, we are expanding access to genomic technology to realize health equity for billions of people around the world. Our efforts enable life-changing discoveries that are transforming human health through the early detection and diagnosis of diseases and new treatment options for patients.

Working at Illumina means being part of something bigger than yourself. Every person, in every role, has the opportunity to make a difference. Surrounded by extraordinary people, inspiring leaders, and world changing projects, you will do more and become more than you ever thought possible.

The Senior Staff AI Engineer, AI Experience is the most senior engineer responsible for the interfaces through which users meet our AI. This role exists because the interface is the product when it comes to AI, and shipping models behind a chat box is no longer enough. We need an engineer who can think simultaneously about prompt design, model behavior, streaming systems, generative interfaces, and the craft of user experience, and who can translate that combined fluency into AI products that feel obvious, trustworthy, and delightful.

This is a deeply technical, hands-on senior IC role. You will write production code across the AI and frontend stack, define the interaction patterns that the rest of the engineering organization adopts, and partner closely with design, research, and product to shape what AI products look and feel like at our company. You will also serve as the technical voice that defines the difference between an AI feature that is technically working and an AI feature that is genuinely usable.

Key Responsibilities

Build AI-Native Interfaces

Design and build production interfaces for AI features including conversational UIs, agentic experiences, generative UI, multi-modal interactions, and artifact-style canvases.

Implement streaming experiences end to end, including token streaming, progressive rendering, structured output streaming, and interruption and resumption patterns.

Build interfaces that surface model behavior intelligibly, including reasoning traces, tool use, citations, confidence signals, and graceful failure states.

Develop reusable component libraries, design system primitives, and frontend patterns for AI features that other product teams adopt across the company.

Shape AI Behavior for the Interface

Engineer prompts, structured output schemas, and tool definitions that produce outputs the UI can render well, including JSON modes, streaming-friendly formats, and component-aware generation.

Define evaluation criteria that measure not only model accuracy but also the quality of the rendered experience, such as latency, intelligibility, perceived responsiveness, and trust signals.

Partner with model and platform teams to ensure model capabilities are exposed in ways that frontend systems can consume reliably.

Define Patterns and Standards

Establish the AI UX patterns the company uses for chat, agents, autocomplete, generative UI, voice, and emerging modalities.

Set standards for streaming behavior, latency budgets, error states, undo and redo semantics, content safety surfacing, and accessibility in AI products.

Lead architecture reviews for AI-facing product features and serve as the senior technical reviewer for high-stakes AI experience initiatives.

Author technical documents, design docs, and internal guides that codify AI experience standards.

Partner Across Disciplines

Work shoulder to shoulder with designers and design engineers to invent and refine AI interaction patterns, often through rapid prototyping rather than static mockups.

Collaborate with product managers and researchers to scope AI features that solve real user problems and to define what good looks like for each release.

Pair with backend and ML engineers to ensure the full system, from model inference through frontend rendering, performs as one coherent experience.

Mentor and Influence

Mentor senior and staff engineers across both AI Engineering and Frontend Engineering, raising the bar for AI experience work across the organization.

Represent AI experience engineering in executive forums, customer conversations, and external engagements such as conferences or community contributions.

Identify and prototype emerging interaction patterns (generative UI, voice agents, multi-modal canvases, ambient AI) and lead the path from experiment to production.

Required Qualifications

12 or more years of professional software engineering experience, with at least 3 years focused on AI or LLM-powered product surfaces.

Deep frontend expertise, including expert-level command of React or a comparable modern framework, TypeScript, modern build tooling, and contemporary CSS and styling systems.

Hands-on production experience integrating LLMs into user-facing applications, including streaming, tool calling, structured outputs, and prompt engineering as it relates to UI consumption.

Demonstrated ownership of flagship AI product surfaces with measurable outcomes in adoption, engagement, or user satisfaction.

Strong design sensibility and proven ability to collaborate as a peer with designers, not merely as an implementer of their work.

Experience defining engineering standards and patterns adopted by multiple teams.

Bachelor's or Master's degree in Computer Science, Human-Computer Interaction, Design, or a related field, or equivalent demonstrable experience.

Preferred Qualifications

Experience building agentic interfaces, including patterns for showing reasoning, tool use, multi-step workflows, and human-in-the-loop interventions.

Background in real-time and collaborative systems, including WebSockets, Server-Sent Events, CRDTs, or operational transforms.

Experience with voice and multimodal interfaces, including ASR, TTS, turn-taking, barge-in handling, and voice agent design.

Familiarity with generative UI patterns where models produce structured UI specifications that the client renders dynamically.

Background in design systems and component library authorship, including accessibility, theming, and cross-platform consistency.

Contributions to open source AI or frontend tooling, public talks, writing, or other forms of visible community engagement.

Familiarity with at least one major LLM provider's tool ecosystem (OpenAI, Anthropic), including their streaming protocols, tool calling formats, and structured output capabilities.

Technical Skill Profile

Frontend: React (expert), TypeScript, Next.js or similar meta-frameworks, modern CSS, Tailwind, animation libraries (Framer Motion), state management (Zustand, Redux, Jotai), testing (Vitest, Playwright).

AI and LLM Integration: Streaming APIs from OpenAI, Anthropic, and tool calling, structured outputs (JSON mode, function calling), prompt engineering for UI consumption, evaluation tooling.

Real-Time and Streaming: Server-Sent Events, WebSockets, streaming JSON parsers, backpressure handling, optimistic UI patterns, partial render strategies.

Backend Touchpoints: Node.js or Python for backend-for-frontend services, REST and GraphQL APIs, edge runtimes (Vercel, Cloudflare Workers).

Tooling and Platform: Git, modern CI/CD, observability for frontend (Sentry, LogRocket), feature flags, A/B testing platforms.

Design and UX: Figma fluency, design tokens, accessibility standards (WCAG), motion design, interaction design fundamentals.

Competencies We Value

Taste: Strong, articulate point of view about what makes an AI product feel great, with the technical chops to build toward that vision.

Cross-Disciplinary Fluency: Genuine respect and curiosity for design, research, and product, with the ability to operate as a peer across all of them.

Builder's Mindset: Bias toward prototyping and shipping rather than abstract debate, including comfort building rough demos to drive decisions.

Systems Thinking: Ability to reason about the full stack from model behavior through network protocols to rendered pixels.

Influence Without Authority: Effectiveness in shaping how other teams build through patterns, libraries, demos, and credibility rather than mandate.

Communication: Clarity in writing, demos, and conversation, including the ability to explain frontend craft to AI engineers and AI nuance to designers.