Forward Deployed Engineer, AI and Agentic SDLC

GitLab’s Forward Deployed Engineering team closes the gap between what strategic customers need and what GitLab can currently deliver. We work alongside customers, Product, Engineering, and existing field teams, using hands-on engineering to resolve product friction, accelerate customer outcomes, and contribute reusable improvements back to GitLab.

As a Staff Forward Deployed Engineer focused on AI and Agentic SDLC, you will help define and build GitLab Duo Agent Platform at the frontier of agentic software development. You will design agent workflows and context systems, build integrations and product changes, evaluate and optimize system behavior, and work directly with customers to understand where AI systems succeed, fail, or create friction.

Engagements may range from a focused technical consultation to a long-running design partnership. The technical work may span GitLab’s CLI, IDE integrations, AI Gateway, web experiences, agent orchestration, evaluation systems, authorization controls, and other evolving parts of the platform.

• Design and build agentic systems using models, tools, action loops, orchestration, context, retrieval, state, memory, evaluation, tracing, and human oversight.
• Develop context and knowledge systems using approaches such as retrieval-augmented generation, cache-augmented generation, graph-based retrieval, repository understanding, and context optimization.
• Work directly in strategic customer environments to understand technical friction and turn ambiguous needs into working solutions.
• Build agent workflows, integrations, evaluation suites, reference architectures, and product capabilities that improve customer outcomes.
• Contribute production-quality changes across GitLab Duo Agent Platform and the broader GitLab product.
• Evaluate and improve system quality, reliability, latency, cost, token use, safety, authorization, governance, and developer experience.
• Diagnose failures across models, context, retrieval, tool use, control flow, product behavior, permissions, and surrounding software-development workflows.
• Partner with Product and Engineering as an extension of their teams, accelerating work while aligning with product direction and engineering standards.
• Generalize customer-specific learning into reusable platform capabilities, implementation patterns, and technical guidance.
• Provide Staff-level technical leadership through architecture, implementation, review, mentorship, and influence across teams.

• Staff-level software-engineering experience building, shipping, and improving complex production systems.
• Hands-on experience designing and building substantive AI systems, with the ability to evaluate, trace, debug, and optimize their behavior.
• Strong understanding of how agentic systems use models, context, retrieval, tools, state, control flow, evaluation, and human oversight.
• Understanding of why AI systems become unreliable, fail to achieve adoption, or consume significant resources without producing useful outcomes.
• Depth in one or more areas of AI engineering, such as agent systems, context and knowledge systems, AI developer tools, inference, or AI-enabled product engineering.
• Strong programming skills in Python, TypeScript, Go, Rust, Java, Kotlin, Ruby, C#, or another language used to build AI, backend, developer-tooling, or platform systems.
• Ability to learn and contribute across large, mature, polyglot codebases.
• Practical understanding of AI safety, authorization, governance, observability, and cost management.
• Ability to communicate clearly with customers and senior stakeholders, work through ambiguity, and build trust while remaining deeply technical.
• A record of Staff-level impact through technical direction, reusable systems, mentorship, cross-team influence, or product architecture.

AI engineering spans multiple disciplines, and we do not expect every candidate to have equal depth across all of them. Strong candidates will bring deep expertise in one or more areas, along with the systems perspective needed to collaborate across the complete platform.

• Experience working directly with customers, design partners, or external engineering teams.
• Experience building AI systems for software development, coding agents, IDEs, code understanding, code review, testing, CI/CD, security, or incident response.
• Experience with LangChain, LangGraph, RAG, cache-augmented generation, knowledge graphs, agent evaluation, tracing, or related systems.
• Experience evaluating how model and inference behavior affects application or agent performance.
• Experience with self-hosted models, restricted environments, enterprise governance, or customer-controlled inference.
• Familiarity with Git, GitLab, CI/CD, developer platforms, or large open-source products.
• Experience with Ruby on Rails or other parts of GitLab’s existing product stack.
• Experience with AWS, GCP, Azure or Kubernetes.
• Experience with Infrastructure as Code tooling, such as Terraform, Ansible, etc.
• Public technical writing, architecture guidance, open-source contributions, talks, or other evidence of technical leadership.