Principal Engineer, Duo Agent Platform

About the role

We are looking for a Principal Engineer to help build GitLab Duo Agent Platform, the agentic orchestration layer that runs AI agents and flows across the entire software lifecycle.

Principal Engineers at GitLab are recognized experts across multiple technology domains and represent the senior technical leadership within their organization. In this role you will set technical direction for a significant part of the Agent Platform, working across several teams to turn agentic capabilities into something engineering organizations can actually depend on: predictable, observable, governable, and fast enough to sit in the critical path of real development work.

The Agent Platform spans agent execution and orchestration, flow definition and event-driven triggering, the AI Catalog, model routing and evaluation, and governance. It runs on GitLab.com, GitLab Dedicated, and Self-Managed installations. This role reports into the VP of the AI Engineering organization and works closely with Engineering Managers, Staff Engineers, Product Management, Infrastructure, and Security.

What you'll do

• Define the technical direction for a significant area of Duo Agent Platform across several teams, partnering with Engineering Managers and Product to turn it into a roadmap with a six-month horizon.
• Build the orchestration layer that makes agents and flows reliable: session lifecycle, tool invocation, context assembly, concurrency, retries, timeouts, and graceful failure modes.
• Deliver hands-on work driving initiatives throughout the organization from POC level and architecture to full implementation.
• Participate in Incident Management on-call rotation to help meet availability goals for GitLab.com.
• Demonstrate a strong product builder and ownership mentality across product strategy, technical strategy, and customer value iteration.
• Write clear, opinionated design documents, architecture narratives, and decision records across multi-tenant GitLab.com, Dedicated, and Self-Managed deployments.
• Use the platform internally, identify shortcomings, and feed improvements back into the product.
• Mentor Staff and Senior Engineers, raising the bar for experimentation rigor and cross-team collaboration.
• Design extensibility surfaces for customers to build custom agents/flows, connect internal systems, and integrate external agents (e.g., Claude Code, Codex).
• Drive down the cost and latency of agentic requests, optimizing model selection, routing, and credit consumption.
• Define the evaluation practice for the platform (offline benchmarks, online experiments) measuring completion, correctness, accuracy, latency, and cost per task.
• Build the governance and safety surface with Security and Compliance: policy-driven controls, permission/identity semantics, human-in-the-loop checkpoints, session traceability, and auditing.
• Complete Interview Training and participate in technical hiring.

What you'll bring

• 8+ years of software engineering experience, including 3+ years at Staff, Principal level, or equivalent senior technical leadership.
• Hands-on production experience building on large language models: agent loops, tool calling, context management, retrieval, prompt and model evaluation shipped to real users.
• Strong background in distributed systems, including service decomposition, fault tolerance, observability, and operational resilience under multi-tenant load.
• Track record of defining evaluation frameworks and using benchmark/experiment results to guide architectural decisions.
• Experience designing human-in-the-loop controls, safety guardrails, and responsible AI practices.
• Ability to drive alignment across Engineering, Product, Infrastructure, and Security on ambiguous problems.
• Experience mentoring senior engineers and shaping technical direction across multiple teams without direct authority.
• Comfort working in one or more of Ruby, Go, Python, or TypeScript, with willingness to work across the stack.
• Excellent written and asynchronous communication skills in a fully remote, globally distributed organization.