Software Engineer, Agent

About the role

Vercel is building an agentic infrastructure platform to automate web development and operations. You will join a specialized team creating autonomous systems that diagnose production issues, manage deployments, and perform complex tasks on behalf of developers. In this role, you will own the design and implementation of systems that can independently investigate and remediate critical production incidents such as 500 errors, build failures, and performance regressions. You will architect multi-step reasoning workflows that intelligently coordinate across external APIs and secure, sandboxed code execution environments while maintaining durable state. A core part of your work will involve creating deep tool integrations that give agents comprehensive knowledge of Vercel platform primitives including DNS, logs, metrics, functions, and deployments. You will also develop the infrastructure that allows agents to dynamically acquire new capabilities at runtime through skill injection mechanisms. Additionally, you will build user-facing experiences for the Vercel dashboard, CLI, and Slack, taking ownership of the entire product journey without relying on external design mockups. Finally, you will collaborate closely on prompt engineering, model evaluation, and RAG pipelines to ensure the accuracy, reliability, and safety of agent behavior in production.

Key facts

What you'll do

• Design and build agentic systems capable of autonomous investigation and remediation of production issues like 500 errors, build failures, and performance regressions.
• Architect workflows for multi-step reasoning that coordinate across APIs and sandboxed code execution environments with durable state.
• Create tool integrations that provide the agent with deep knowledge of Vercel platform primitives including DNS, logs, metrics, functions, and deployments.
• Develop infrastructure for dynamic skill injection to allow agents to acquire new capabilities at runtime.
• Build user-facing experiences for the Vercel dashboard, CLI, and Slack without relying on external design mockups.
• Collaborate on prompt engineering, model evaluation, and RAG pipelines to ensure agent accuracy.
• Implement robust observability and debugging tools specifically for agent workflows to enable rapid diagnosis of issues.
• Partner with product and design to define the next generation of autonomous developer tools and workflows.
• Write high-quality, maintainable code that adheres to strict standards for security, performance, and scalability.
• Contribute to open source projects and internal libraries that abstract complex agentic interactions into reusable components.
• Mentor junior engineers by conducting code reviews, providing constructive feedback, and sharing knowledge about agentic systems.
• Participate in on-call rotations to respond to critical issues affecting agent performance in production.
• Conduct experiments to measure agent effectiveness and use data to drive improvements in autonomy and reliability.
• Ensure compliance with internal security policies and best practices when integrating with external services and APIs.

Requirements

• 7+ years of professional software engineering experience.
• Proficiency in TypeScript or deep experience in Python with a willingness to work primarily in TypeScript.
• Strong product and UI sensibility with the ability to ship polished interfaces independently.
• Full-stack technical background with knowledge of infrastructure, CI/CD, observability, and large-scale web applications.
• Experience building or contributing to frameworks, platforms, or reusable abstractions.
• Ability to work independently, set technical direction, and communicate complex concepts to partner teams.
• Adaptability to learn and apply new technologies in a rapidly changing field.
• Demonstrated skill in debugging complex distributed systems and resolving issues in production environments.
• Comfort working with REST and GraphQL APIs to integrate diverse services into cohesive agent workflows.
• Understanding of security fundamentals such as authentication, authorization, and secret management in cloud environments.
• Experience with testing strategies for agentic systems, including unit, integration, and end-to-end tests.
• Strong written and verbal communication skills for collaborating with cross-functional teams.
• Commitment to writing clean, well-documented code that can be maintained by other engineers over the long term.
• Willingness to engage in technical design discussions and make thoughtful trade-offs in system architecture.

Nice to have

• Experience deploying agentic systems, AI tooling, or automation frameworks into production environments.
• Familiarity with LLM APIs such as OpenAI or Anthropic, prompt engineering, and RAG.
• Prior work with Vercel, Next.js, or the modern web deployment ecosystem.
• Background in sandboxed execution environments, secure multi-tenant systems, or container orchestration.
• Knowledge of observability platforms such as logs, metrics, and tracing systems like Datadog, New Relic, or similar.
• Experience with infrastructure as code tools and version control workflows.
• Understanding of performance optimization techniques for web applications at scale.
• Familiarity with accessibility standards and inclusive design principles.
• Contributions to the developer community through talks, blog posts, or open source projects.
• Experience mentoring or leading small engineering initiatives.

Practical notes

• If you are within commuting distance of the San Francisco, New York, London, or Berlin offices, this role requires in-office attendance on Mondays, Tuesdays, and Fridays.
• Compensation includes a competitive salary and equity.
• Benefits include an inclusive healthcare package and a learning and growth budget.
• This is a full-time position based in the San Francisco office with a hybrid schedule.
• Applicants must be authorized to work in the country where the role is based at the time of application.
• The hiring process may include technical assessments, take-home assignments, and interviews with members of the Agent team.
• Vercel is an equal opportunity employer and welcomes applicants from diverse backgrounds.
• Only candidates who closely match the requirements will be contacted for the next steps.
• The role involves frequent collaboration with product, design, and engineering teams across time zones.
• You should expect to engage in continuous learning and professional development as part of your day-to-day responsibilities.
• The successful candidate will be expected to contribute to incident response on a rotating basis.
• This position reports to the Agent team and works closely with engineering leadership.
• All decisions regarding compensation and equity will be made based on market data and internal guidelines.
• The company reserves the right to adjust job responsibilities as needed to meet evolving business needs.
• You will be expected to maintain a high standard of professionalism and ownership in all interactions with colleagues and stakeholders.
• The role requires a proactive approach to identifying risks and proposing solutions before issues impact customers.
• You will work closely with security and infrastructure teams to ensure that all integrations meet organizational standards.
• The position involves regular interaction with stakeholders to gather requirements and provide status updates.
• You should be comfortable working in an agile environment with frequent iterations and changing priorities.
• The role includes responsibility for documenting architectural decisions and trade-offs for future reference.
• You will be expected to participate in hiring interviews for future engineers within the Agent team.
• The successful candidate will have opportunities to present their work at internal forums and contribute to technical roadmaps.
• This role is part of a growing organization and offers significant room for impact as the agentic platform evolves.