About this role.
Vercel is hiring a senior software engineer to build V, an internal agentic interface that can answer questions, analyze data, and execute complex workflows across the company. The role spans agent architecture, tool orchestration, reliability, evaluation systems, observability, and polished Slack and web experiences. Candidates need 7+ years of full-time engineering experience, strong TypeScript skills, and comfort working across frontend, backend, data, permissions, and production infrastructure. Success requires strong judgment around AI interaction quality, including context, memory, latency, uncertainty, and user-facing progress communication. This is a high-impact role helping define how an organization can be operated through AI agents.
Role DNA
A quick view of the complexity, pace, ownership and collaboration implied by the job description.
Job Complexity
5/5Pace & Pressure
5/5Autonomy Level
5/5Communication Load
5/5Salary analysis
Estimated compensation compared with the broader US market for similar roles.
Core skills
Skills and capabilities most closely associated with this opportunity.
Cover letter sample
Dear Vercel Hiring Team,
I am excited to apply for the Member of the Technical Staff, Internal Agent role. My background in building production software across TypeScript applications, APIs, data systems, and reliable platform infrastructure aligns well with Vercel's goal of creating a trusted internal agentic interface.
I am particularly motivated by the opportunity to improve agent planning, tool use, evaluations, observability, and human-centered interaction design across Slack and web experiences. I would bring strong technical judgment, curiosity, and a collaborative approach to building durable primitives that enable teams to safely contribute new capabilities.
Thank you for your consideration; I would welcome the opportunity to discuss how I can help shape V and the future of agent-operated workflows at Vercel.
Sample interview questions
I would model the workflow as a durable state machine with explicit plans, idempotent tool actions, checkpoints, retries, timeouts, and clear recovery paths. Each tool call would have structured inputs and outputs, authorization checks, audit logs, and correlation IDs. I would expose progress and uncertainty to the user while routing failures to safe fallback or human-review steps.
I would combine offline evaluation sets with production telemetry and user feedback. Metrics would include task completion, factual and action accuracy, tool-call success, latency, cost, recovery rate, user correction rate, and confidence calibration. For consequential actions, I would also measure policy compliance and require approval thresholds where appropriate.
I would separate short-term task state from durable user or organizational memory and retrieve only information relevant to the current intent. Context should be permission-aware, attributable, fresh, and bounded by token and latency budgets. I would use summaries and structured state for long-running work, with users able to inspect or correct important stored information.
Chat is effective for concise questions, clarification, and lightweight actions, while interactive interfaces are better for reviewing data, configuring parameters, comparing alternatives, and approving consequential steps. I would choose the surface based on task complexity, reversibility, information density, and the user's need for control. The experience should allow smooth transitions between natural language and structured UI.
I would provide shared primitives for tool definitions, identity and permissions, interaction patterns, evaluation, observability, and release controls. Capabilities should follow clear contracts, ownership standards, and compatibility requirements, with a centralized registry and discovery model. This allows local innovation while preserving consistent behavior, safety, and user experience.
About Vercel:
Vercel is the agentic infrastructure company. We free people and agents to ship what’s next.
For more than a decade, Vercel has shaped how the web is built. As the team behind Next.js, v0, and AI SDK, we create products that help builders move from idea to production with speed, security, and exceptional developer experience.
Now, software is entering a new era, and the next generation of products will not just be used by people. They will be built, extended, and operated by agents.
We are building the platform for that future, trusted by companies like OpenAI, PayPal, Ramp, Supreme, and millions of developers worldwide. Whether you’re building our products, supporting our customers, growing our community, or shaping our story, you’ll help define what comes next.
What You Will Do:
- 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.
About You:
- 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
Benefits:
- Competitive compensation package, including equity.
- Inclusive Healthcare Package.
- Learn and Grow – we provide mentorship and send you to events that help you build your network and skills.
- Flexible Time Off.
- We will provide you the gear you need to do your role, and a WFH budget for you to outfit your space as needed.
The San Francisco, CA base pay range for this role is $208,000 – $312,000. Actual salary will be based on job-related skills, experience, and location. Compensation outside of San Francisco may be adjusted based on employee location. The total compensation package may include benefits, equity-based compensation, and eligibility for a company bonus or variable pay program depending on the role. Your recruiter can share more details during the hiring process.
Vercel is committed to fostering and empowering an inclusive community within our organization. We do not discriminate on the basis of race, religion, color, gender expression or identity, sexual orientation, national origin, citizenship, age, marital status, veteran status, disability status, or any other characteristic protected by law. Vercel encourages everyone to apply for our available positions, even if they don’t necessarily check every box on the job description.
Upload your resume now
- To unlock remote work opportunities and be discovered by global employers.
This job listing has been manually reviewed by the Jobicy Trust & Safety Team for compliance with our posting guidelines, including verification of the company's legitimacy, accuracy of job details, clarity of remote work policy, and absence of misleading or fraudulent content.
