Software Engineer, Agent

About Vercel: Vercel gives developers the tools and cloud infrastructure to build, scale, and secure a faster, more personalized web. As the team behind v0, Next.js, and AI SDK, Vercel helps customers like Ramp, Supreme, PayPal, and Under Armour build for the AI-native web. Our mission is to enable the world to ship the best products. That starts with creating a place where everyone can do their best work. Whether you're building on our platform, supporting our customers, or shaping our story: You can just ship things.   About the role: We’re looking for a Software  Engineer  to join the  Vercel  Agent team. Our mission is simple: deploying on  Vercel  should feel like adding a seasoned  infrastructure   engineer  to your team. The  Vercel  Agent investigates incidents before you see them, fixes failing builds, reviews  code  with deep  production  context, and answers questions about your  running  app with the authority of someone who has read the logs. Today, this work spans multiple shipped  products:  automated  code  review on every PR,  AI -driven investigation of  production  anomalies, an intelligent support agent that resolves the majority of customer issues without human intervention, and conversational  code   generation . We’re now unifying these into a single agent that appears pervasively across surfaces (like the  Vercel  dashboard,  Vercel  CLI, Slack, and many more), and is capable of multi-step reasoning,  code  execution in sandboxed environments, and taking real actions on your behalf. Two things we’re most excited about:  self-driving  infrastructure , where 90% of what requires manual DevOps today gets handled automatically by the  platform ; and  framework-defined agents , where the agent is customized to each customer’s application, injecting the right skills when they’re needed rather than dumping generic best practices. This is a small team with an outsized mandate. You’ll work directly with leadership and across  product,   design , and  infrastructure  teams to define what self-driving  infrastructure  looks like — then  build  it. If you’re based within a pre-determined commuting distance of one of our offices (SF, NY, London, or Berlin), the role includes in-office anchor days on Monday, Tuesday, and Friday, even if the role is listed as remote. For location-specific details, please connect with our recruiting team. What you will do: Design  and  build  agentic  systems  that autonomously investigate, diagnose, and remediate  production  issues — from 500 errors and  build  failures to  performance  regressions and security anomalies. Architect multi-step agent workflows that coordinate across tools,  APIs , and sandboxed  code  execution environments, with durable state that survives crashes and timeouts. Build  the skills and  tool   integrations  that give the agent deep knowledge of the  Vercel   platform , such as deployments, functions, logs, metrics, DNS, and the full lifecycle of a web application. Ship polished,  user -facing experiences across multiple surfaces (Slack, dashboard, CLI) without waiting for a designer to hand you a mockup. This team values  engineers  with strong  product  and UI instincts. Develop  the  infrastructure  for dynamic skill injection, so the agent acquires new capabilities at runtime rather than through redeployment, routing the right logic to the right context at the right time. Collaborate with other  engineers  on prompt  engineering,  model evaluation, and retrieval-augmented  generation  (RAG)  pipelines  that ground the agent in accurate, up-to-date knowledge. About you: 7+ years of full-time software  engineering  experience, with strong  TypeScript  proficiency.  Engineers  with deep Python experience who are excited to work in  TypeScript  are also a great fit. A track record of  openness  and adaptability: you’ve shifted into new technologies, new domains, or new roles and thrived. This space is changing faster than anyone can claim expertise; we want people who learn and adapt, not people who play expert. Strong  product  and UI sensibility. You care about the details of how an  AI  interaction feels to a  user , and you can  build  great experiences without waiting for a designer. Full-stack  capability with an understanding of  infrastructure , CI/CD, observability, and how large-scale web  applications  operate. The agent needs to reason about the same  systems  our customers use every day, you should too. Experience  building  or contributing to frameworks, platforms, or reusable abstractions, not just  feature  work. You know when to  build  a primitive versus ship a one-off. Demonstrated ability to ship independently, influence architecture, and set direction on a small, high-impact team. Excellent communication skills, with an ability to translate technical det