Agentic Operator - Growth Marketing

1d1 day ago

Ramp

New York City, US · Full-time · $168,000 – $231,000

About this role

Ramp is building the smart infrastructure for finance teams, embedded in the transaction flow of every dollar a business spends. We automate how over $100B in annualized spend flows in and out of 50,000+ companies. The problems are high-stakes, data-dense, and unforgiving.

We're looking for an AI Agent Operator and Architect to join the team that designs, builds, and operates AI agents for our Marketing team. This isn't a role where you use AI to work faster. It's a role where you build AI that does the work and recursively learns.

You'll take marketing workflows and break them down into agent architectures: skills, tools, evals, memory, and orchestration layers that run 24/7 and get better on their own. Our marketing team already deeply leverages AI. Your job is to take us from AI-assisted to agent-operated.

Everyone at Ramp is a builder who owns problems end to end and makes consequential decisions. The median Ramp customer saves 5% and grows revenue 16% in their first year. If you want to build systems that directly shape how companies move and manage billions, Ramp is the place to do it.

Requirements

Can mock up an MVP and then go build the thing, scoping what matters and shipping it yourself with PM brain and engineer hands.
Extremely AI-pilled with strong opinions on tool-use vs. code-gen agents, when to use RAG vs. fine-tuning, and how to build evals that actually matter.
Think in systems and loops, designing processes where agents trigger other agents and outputs become inputs that compound without someone pressing run.
Have built and shipped agents in production, not something theoretical.

Responsibilities

Build AI agents from scratch that autonomously run marketing workflows including content generation, campaign development, paid channel optimization, and creative testing.
Break down workflows into the pieces agents need: skills, tools, evals, guardrails, memory, and feedback loops.
Build evaluation frameworks that measure agent quality, catch regressions, and drive improvement without someone babysitting the system.
Design self-improving loops where agents monitor their own outputs, learn from outcomes, and get sharper over time.
Own everything from identifying which workflows to automate, to prototyping, to production deployment, to monitoring and iteration.
Stay plugged into the cutting edge of agentic AI, new model capabilities, tool-use patterns, multi-agent orchestration, and evals frameworks.
Build reusable agent infrastructure, internal tooling, and documentation so the rest of the marketing team can operate and trust what you've built.