Design and build V as the primary agentic interface for getting work done across Vercel, from answering questions and analyzing data to executing complex, multi-system workflows
Build the agent architecture that allows V to understand intent, plan work, select the right skills and tools, recover from failures, and complete long-running tasks reliably
Ship polished experiences across Slack, web, and other surfaces, combining natural-language interaction with rich, interactive interfaces when chat alone is not enough
Develop evaluation, observability, and feedback systems that measure whether V’s answers and actions are accurate, useful, efficient, and trustworthy
Establish primitives that make it easy for teams across Vercel to contribute new capabilities without creating fragmented agents or inconsistent user experiences
Help define what it means for a company to be operated through an agent and turn what we learn building V into ideas and infrastructure that can eventually benefit Vercel’s customers
You have 7+ years of full-time software engineering experience and strong TypeScript proficiency
You are comfortable working across product surfaces and system boundaries, from conversational UI and interactive data experiences to APIs, queues, databases, permissions, and production infrastructure
You care about the quality of AI interactions: context selection, tool use, memory, latency, generated interfaces, uncertainty, and how the system communicates progress and asks for help
You have a track record of openness and adaptability. You have moved into unfamiliar technologies, domains, or responsibilities and learned quickly. This space is changing too quickly for fixed expertise to matter more than curiosity and judgment
Experience with using and building agent harnesses (OpenClaw, Hermes, Pi, etc) is a plus but not required