AI Engineer

The role

You will build systems that build systems, including agent harnesses and sub-agents. You will deliver new toolkits, abilities, and services to enable agents to take actions in enterprise systems.

What you will do

• Build dedicated agent harnesses that write and maintain tools themselves
• Build agents-as-tools that let one agent call another as a capability
• Take a job to be done and own delivering it
• Build new toolkits and abilities from vendor APIs or internal needs
• Fix rough edges when agents hit walls
• Maintain and improve the existing catalog
• Build the next generation of evaluation and testing for abilities
• Engage with and push the MCP ecosystem

Required qualifications

• 4+ years of software engineering experience shipping production code
• Track record of owning projects end to end
• Strong Python and/or TypeScript
• Experience building and consuming APIs at scale
• LLM application experience
• A testing mindset
• Comfort with ambiguity

Nice to have

• Familiarity with the MCP (Model Context Protocol) ecosystem or similar agent-tool protocols
• Familiarity with Go
• Built evals or measurement systems for ML/AI behavior
• Prior experience at an API platform, data-warehouse, integrations-heavy product, or developer tools company
• Open-source contributions
• Experience at an early-stage startup

Benefits

• Competitive salary
• Equity
• Competitive benefits

About the company

Arcade is the MCP runtime that gives agents the power to connect to systems and perform actions with authorization and governance. The company is building critical infrastructure for enterprise agents.