Senior Backend Engineer, Trusted Agentic Development

GitLab is the intelligent orchestration platform for DevSecOps. GitLab enables organizations to increase developer productivity, improve operational efficiency, reduce security and compliance risk, and accelerate digital transformation. More than 50 million registered users and more than 50% of the Fortune 100* trust GitLab to ship better, more secure software faster.

The same principles built into our products are reflected in how our team works: we embrace AI as a core productivity multiplier, with all team members expected to incorporate AI into their daily workflows to drive efficiency, innovation, and impact. GitLab is where careers accelerate, innovation flourishes, and every voice is valued. Our high-performance culture is driven by our values and continuous knowledge exchange, enabling our team members to reach their full potential while collaborating with industry leaders to solve complex problems. Co-create the future with us as we build technology that transforms how the world develops software.

*Fortune 500® is a registered trademark of Fortune Media IP Limited, used under license. Claim based on GitLab data. Fortune 100 refers to the top 20% ranked companies in the 2025 Fortune 500 list, published in June 2025. Fortune and Fortune Media IP Limited are not affiliated with, and do not endorse products or services of GitLab.

An overview of this role

The Trusted Agentic Development team sits within GitLab's Developer Experience group and builds the platforms our engineers rely on every day. GitLab engineers increasingly build software with artificial intelligence agents. Agents can generate code and tests in seconds, but they can also produce passing test suites for software that doesn't work as intended. As a Senior Backend Engineer, Trusted Agentic Development, you'll own the technical thesis for closing that validation gap and build the early proof yourself. You'll rethink what validation means when the author is an agent and make the feedback loop fast, automatic, and trustworthy enough that teams choose to adopt it.

Validation that confirms agent-generated code does what was intended, so a passing suite means a working feature and not just a satisfied proxy.

Mid-loop feedback that helps an agent self-correct toward working software instead of green assertions.

Language-aware approaches under one shared model of what "trusted" means, starting with Rust, Ruby, and Go, while allowing the right technique to differ by language.

Real measurement of whether engineers trust and adopt the path, fed straight back into the platform.

What you’ll do

Own the technical thesis for how GitLab validates software when an agent is the author, and turn it into an architecture the team can build against.

Prototype the hard parts by building early versions of feedback mechanisms that catch the gap between passing tests and working software, proving what works before the team scales it.

Develop approaches for GitLab's primary stacks, starting with Rust, Ruby, and Go, under one shared definition of "trusted," while allowing the right technique to differ by language.

Design the mid-loop feedback an agent needs to self-correct toward working software rather than green assertions, and build the systems that deliver it.

Collaborate with engineering teams to adopt these approaches, measure adoption, engineer trust, and validation quality, and use those findings to improve the platform.

Set technical direction the team can build on, review designs, and help teammates grow their technical judgment.

What you’ll bring

Deep, current, hands-on experience building real software with artificial intelligence agents, ideally across more than one language, and a clear understanding of why agent output can pass tests yet fail in production.

A strong point of view on the validation gap and concrete ideas for closing it, backed by approaches you've built or tried.

The technical range to design systems rather than tune a single framework,