Software Engineer, Agent

Vercel Vercel · Enterprise · United States · Remote · Engineering

Software Engineer to join the Vercel Agent team, focusing on building agentic systems for self-driving infrastructure and framework-defined agents. The role involves designing and building multi-step agent workflows, tool integrations, and user-facing experiences across various Vercel surfaces. Emphasis on full-stack capabilities, product sense, and shipping independently.

What you'd actually do

  1. 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.
  2. Architect multi-step agent workflows that coordinate across tools, APIs, and sandboxed code execution environments, with durable state that survives crashes and timeouts.
  3. 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.
  4. 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.
  5. 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.

Skills

Required

  • 7+ years of full-time software engineering experience
  • strong TypeScript proficiency
  • Full-stack capability
  • understanding of infrastructure, CI/CD, observability
  • how large-scale web applications operate
  • Experience building or contributing to frameworks, platforms, or reusable abstractions
  • Demonstrated ability to ship independently, influence architecture, and set direction
  • Excellent communication skills

Nice to have

  • deep Python experience
  • strong product and UI sensibility
  • experience building agentic systems, AI tooling, or automation frameworks
  • agents in production
  • familiar with LLM APIs (Anthropic, OpenAI, etc.)
  • prompt engineering
  • retrieval-augmented generation (RAG)
  • worked with Vercel, Next.js, or the modern web deployment ecosystem
  • experience with sandboxed execution environments, container orchestration, or secure multi-tenant systems

What the JD emphasized

  • production issues
  • multi-step agent workflows
  • code execution environments
  • Vercel platform
  • user-facing experiences
  • AI interaction feels to a user
  • large-scale web applications
  • frameworks, platforms, or reusable abstractions
  • shipping independently
  • influence architecture
  • set direction
  • agentic systems
  • agents in production
  • reliably at scale
  • LLM APIs
  • prompt engineering
  • retrieval-augmented generation (RAG)
  • sandboxed execution environments
  • container orchestration
  • secure multi-tenant systems

Other signals

  • AI-native web
  • Vercel Agent
  • self-driving infrastructure
  • framework-defined agents