Member of Technical Staff, CI/CD Infrastructure

Inferact's mission is to grow vLLM as the world's AI inference engine and accelerate AI progress by making inference cheaper and faster. Founded by the creators and core maintainers of vLLM, we sit at the intersection of models and hardware—a position that took years to build.

About the Role

We're looking for a Continuous Integration Infrastructure Engineer to make vLLM development fast, reliable, and scalable. As vLLM grows across models, hardware backends, kernels, and serving environments, the CI system becomes critical infrastructure for the entire engineering organization.

You'll own and improve CI/CD pipelines, build and test infrastructure, containerized environments, Kubernetes-based execution, and GPU-enabled test workflows. Your work will help engineers ship faster with confidence, catch regressions earlier, and maintain reliable development velocity across a complex open-source inference engine.

Skills and Qualifications

Minimum qualifications:

• Bachelor's degree or equivalent experience in computer science, engineering, infrastructure, systems, or similar.

• Strong experience with Docker, Kubernetes, and containerized build or test environments.

• Experience maintaining CI/CD pipelines using GitHub Actions, Buildkite, or similar systems.

• Strong scripting or programming ability in Python, Bash, Go, or similar for build automation, test orchestration, and infrastructure tooling.

• Experience debugging flaky tests, failed builds, dependency issues, caching problems, runner failures, or environment drift.

• Solid Linux, networking, storage, package management, and systems troubleshooting fundamentals.

• Ability to design CI systems that are reliable, observable, fast, and easy for engineers to use.

Preferred qualifications:

• Experience setting up GPU-backed CI or test infrastructure for ML, inference, CUDA, ROCm, or accelerator-heavy workloads.

• Experience with Buildkite at scale, including agents, queues, dynamic pipelines, test sharding, caching, and artifact management.

• Experience operating Kubernetes clusters for CI, batch jobs, test execution, or internal developer infrastructure.

• Experience with large open-source or monorepo-style projects where CI reliability directly affects developer velocity.

• Experience improving CI performance, cost efficiency, test coverage, and regression detection for complex software projects.

Bonus points if you have:

• Built GPU-enabled CI systems for ML frameworks, inference engines, compiler projects, or systems-heavy open-source projects.

• Maintained GitHub Actions or Buildkite pipelines for high-volume engineering teams or open-source communities.

• Implemented test sharding, caching, remote execution, build acceleration, or automated retry strategies that materially improved CI throughput.

• Debugged CI failures involving Docker, Kubernetes, GPU drivers, CUDA / ROCm libraries, or hardware-specific test environments.

• Created dashboards, alerts, runbooks, or tooling that made CI health visible and actionable for engineers.

Logistics

• Location: This role is based in San Francisco, California. Will consider remote in the US for exceptional candidates.

• Compensation: Depending on background, skills, and experience, the expected annual salary range for this position is $200,000 - $400,000 USD + equity.

• Visa sponsorship: We sponsor visas on a case-by-case basis.

• Benefits: Inferact offers generous health, dental, and vision benefits as well as 401(k) company match.