Senior Backend Engineer, Trusted Agentic Development
Tech Stack
Tag name is followed by "@" symbol and proficiency level value.
About proficiency levels:
- 1-2 — basic awareness. Minimal hands-on experience, and a rudimentary understanding of the technology's purpose;
- 3-6 — daily use. Comfortable and regular usage, capable of handling common tasks and challenges related to the technology;
- 7-9 — you are an expert, you can teach others, you know all the pitfalls and tricks;
- 10 — exceptional knowledge, comprehensive understanding, and adeptness in all aspects of the technology, including advanced problem-solving. Think twice before claiming or demanding such level.
AI
Communication @ 7
Go
Ruby
Rust
- 1-2 — basic awareness. Minimal hands-on experience, and a rudimentary understanding of the technology's purpose;
- 3-6 — daily use. Comfortable and regular usage, capable of handling common tasks and challenges related to the technology;
- 7-9 — you are an expert, you can teach others, you know all the pitfalls and tricks;
- 10 — exceptional knowledge, comprehensive understanding, and adeptness in all aspects of the technology, including advanced problem-solving. Think twice before claiming or demanding such level.
Details
GitLab's Trusted Agentic Development team, part of the Developer Experience group, builds platforms that help engineers validate software generated by artificial intelligence agents. The role focuses on closing the validation gap between passing tests and software that works as intended in production.
Responsibilities
- Own the technical thesis for validating software when an AI agent is the author and turn it into an architecture the team can build against.
- Prototype feedback mechanisms that identify the gap between passing tests and working software, proving what works before scaling it.
- Develop approaches for GitLab's primary technology stacks, starting with Rust, Ruby, and Go, under a shared definition of trusted development while allowing language-specific techniques.
- Design and build mid-loop feedback systems that help agents self-correct toward working software rather than merely passing assertions.
- Collaborate with engineering teams to adopt these approaches, measure adoption, engineer trust, and evaluate validation quality.
- Set technical direction, review designs, and help teammates develop their technical judgment.
Requirements
- Deep, current, hands-on experience building real software with artificial intelligence agents, ideally across more than one language.
- Clear understanding of why agent-generated output can pass tests yet fail in production.
- A strong perspective on the validation gap, supported by concrete approaches that have been built or tried.
- Technical range to design systems rather than tune a single framework, with the judgment to determine when solutions should be general or language-specific.
- A prototyping mindset and ability to ship.
- Ability to influence engineers across an organization without formal authority through working code and sound reasoning.
- Strong written communication in an all-remote, asynchronous environment.
- Alignment with GitLab's values, especially collaboration, iteration, and transparency.
This is not a quality assurance or test automation role and does not require depth in a particular testing framework. The team is seeking someone who has built with agents, experienced the validation gap firsthand, and wants to solve it.
About the Team
The Trusted Agentic Development team works across engineering teams and programming languages to understand how people use agents, test new approaches in real workflows, and create a shared model of trusted agentic development that teams choose to adopt.
Benefits
- Benefits supporting health, finances, and well-being.
- Flexible paid time off.
- Team Member Resource Groups.
- Equity compensation and Employee Stock Purchase Plan.
- Growth and Development Fund.
- Parental leave.
GitLab is an equal opportunity workplace and supports accommodations during the recruiting process.