Backend Engineer (Ruby), AI Engineering: Duo Agent Platform Tools

An overview of this role

As an Intermediate Backend Engineer on the GitLab Agent Tools team, you'll go beyond using AI tools and help define how we design, build systems that allow AI agents to interact with the full software delivery lifecycle, way beyond pure code creation.  This encompasses GitLab’s MCP server as well as future technologies that are aimed at providing AI agents ways to interact with GitLab.

In this role you’ll contribute to the development of complex features and help establish architectural patterns for how GitLab exposes its rich functionality to AI agents. You’ll collaborate closely with engineers across the Agent Foundations stage and adjacent teams within AI engineering. This is a high-visibility area of the product at the intersection of GitLab's core platform and its AI strategy.

What you'll do

• Develop, ship, and maintain features and improvements for Agentic Tools across the GitLab monolith backend in a secure, well-tested, and performant way.
• Collaborate with Product Management, UX, frontend, backend, and AI specialists to refine requirements and deliver high-quality, iterative product enhancements.
• Design, implement, and review GraphQL, REST APIs and related backend logic, ensuring reliability, scalability, and clear contracts with frontend clients.
• Improve and extend automated testing, including RSpec and other frameworks, to strengthen quality, reliability, and developer feedback loops.
• Share standards, patterns, and learnings with other engineers, raising the bar for responsible AI integration and evidence-driven engineering across the team.
• Participate in Tier 2 on-call rotations to troubleshoot production issues, contribute to root cause analysis, and enhance observability and resiliency

What you'll bring

• Experience building and maintaining production applications with Ruby on Rails, including work with background jobs, APIs, and data models.
• Comfortable working across the stack in a mature codebase. Familiarity with Python backends and/or Vue frontends a plus.
• Proficiency in designing or extending REST and/or GraphQL APIs with attention to scalability, maintainability, and backward compatibility.
• Strong practical experience working with AI tooling on a daily basis. Experience designing and shipping AI-powered backend features and integrations is a plus
• SQL skills and familiarity with relational databases such as PostgreSQL, including writing efficient queries and understanding data modeling.
• Openness to learning, collaborating in an async-first, distributed team, and applying transferable skills from related technologies or domains.
• Clear written and verbal communication skills, including writing technical proposals and documentation, and collaborating effectively in a remote, asynchronous, cross-functional environment.

About the team

Agent Tools is a new functional team within the Agent Execution group. The team itself will initially consist of three engineers across AMER and EMEA timezones. The whole Agent Execution group consists of 8+ engineers. Beyond the Agent Tools team, Agent Execution consists of further teams focussed on agent observability and executing agents on GitLab’s runners. We’re partnering with teams both within the AI space as well as all over GitLab to ensure that the Duo Agent Platform can become the backbone of many AI features at GitLab.