Senior Staff Full Stack Engineer - Agent Platform, Firefly Boards

Adobe•San Jose, CA

7d•Remote

About The Position

We're seeking a Senior Staff Engineer to lead the Agent Platform work for Firefly Boards. Boards is bringing agentic AI to the infinite canvas, and this role owns the engineering systems that make that work production-grade: the server-side agent runtime, the integration with Adobe's central agent platform, and the application stack that lets the agent act on the canvas alongside human users in real time. You'll partner closely with the agentic team that owns the intelligence side of the product (skills, model selection, agent quality), with a deliberate split of responsibilities. They define what the agent does and how well it does it. You define the systems it runs on. Firefly Boards is an AI-powered mood-boarding and ideation app that provides a non-linear infinite canvas. It enables a new generation of creatives to embrace generative AI and those who find the linear workflows of legacy software restrictive. Images and videos can be imported or generated using AI models and edited, remixed, iterated on, and organized flexibly, making it easier for artists to visualize and develop ideas on their own or in collaboration.

Requirements

Bachelor's Degree or equivalent experience in Computer Science
10+ years of product engineering experience, with significant ownership of production systems at scale
Demonstrated full stack depth: backend services and modern web client work in roughly equal measure. JavaScript/TypeScript, declarative UI frameworks (React, Lit, Vue), and a strong server-side language
Distributed systems depth. Real experience with state management, checkpointing, async work, long-running operations, and recovery from partial failure. Track record of designing and operating systems with these properties, not just consuming them
Experience integrating with a central platform team as a tenant. Has done the work of being an early customer of an internal platform and shaping it from that position
Experience designing service APIs and microservices, including REST or equivalent contracts that hold up across teams
Experience driving sophisticated software architecture, design, and development across multiple teams or organizations
Track record of writing clean, testable code and creating reusable components
Strong written and verbal communication. Comfortable shaping technical decisions in cross-org forums

Nice To Haves

Experience building agentic or retrieval-augmented (RAG) systems with workflow engines such as LangGraph, or comparable runtime orchestration for tool-using LLM applications
Experience with real-time collaborative or multiplayer applications, especially the browser/server boundary in a collaborative editor
Familiarity with MCP (Model Context Protocol) and agent tool design patterns
Experience with production LLM systems: evaluation infrastructure, observability, latency optimization, prompt and context engineering at the system level
Experience with collaborative document models or CRDT-based systems
Experience building image, video, or multimedia applications
Experience with development tools such as Jenkins, GitHub, lint, etc.
Experience with improving performance and stability of large web applications
Experience with Accessibility (A11y) and Localization
Experience working in an Agile development environment

Responsibilities

Stand up and own the service that runs Boards' agent workflows. State management, checkpointing, interrupt-and-resume across long-running operations, error recovery, and observability.
Define and own how server-side workflows dispatch to browser-only tools (canvas operations, viewport state, selection) and resume cleanly. Design the protocol, the runtime contract, and the in-client tool registration and invocation surface. Make it reliable under multiplayer conditions where humans and agents are editing the same document.
Own the integration between Boards' agent runtime and Adobe's central agent platform. Co-shape platform contracts where Boards needs services that don't yet exist in the platform-supported shape.
Refactoring existing Boards APIs and adding new ones to be agent-callable. API design under real constraints: idempotency, transactional boundaries, undo, multiplayer-aware mutations.
End-to-end observability and tracing for agent runs.
Latency budgets across runtime, tools, and model calls.
Deployment, rollout, rollback.
Set engineering direction for the agent platform work and partner across organizational boundaries to make the integration with Adobe's central agent platform succeed.