AI Engineer - Tools
On-siteSan Francisco, California, United States
Job Summary
Build internal agents to maintain and scale the toolkits and skills that power Arcade. Create new toolkits by converting vendor APIs into reliable, high-quality tools for agent consumption. Maintain the existing catalog by fixing breakages, refining descriptions, and adapting to upstream API changes. Write tests and evals that verify tool behavior against real API responses and across different models. Tune tool descriptions and agent calling behavior to treat LLMs as a first-class component. Contribute shared patterns and tooling to accelerate future toolkit development while engaging with the evolving MCP ecosystem.
Required Qualifications
- 4+ years of software engineering experience shipping production code
- Strong Python
- Strong Typescript
- Experience building and consuming APIs — REST, auth flows, pagination, rate limits, and the messy parts of real-world integrations
- A testing mindset — you write tests that catch real failures, not just green checkmarks
- Comfort with ambiguity — early team, a narrow charter that will expand, decisions made with incomplete data
- An insatiable desire to ship
Desired Qualifications
- LLM application experience — prompting, retrieval, tool use, or agent design
- Familiarity with the MCP (Model Context Protocol) ecosystem or similar agent-tool protocols — extra bonus if you've filed an issue against the spec
- You've built evals or measurement systems for ML/AI behavior
- Prior experience at an API platform, integrations-heavy product, or developer tools company
- Open-source contributions
- Experience at an early-stage startup, and you loved it
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.