- Palo Alto, California, United States
- On-site
- Full-time · Staff
- $200K–$400K per year
- 3+ years
Own the infrastructure that keeps SGLang moving, architecting CI systems to ensure fast, trustworthy, and secure commits for a growing open-source LLM inference engine.
Compensation
Depending on background, skills, and experience, the expected annual salary range for this position is $200,000 - $400,000 USD + equity.
Responsibilities
- Own CI reliability end-to-end — triage failures, distinguish real regressions from flaky tests and infra issues, keep main green
- Build regression-based CI — replace hardcoded static thresholds with automated baseline comparison
- Harden runner infrastructure — ephemeral runners, container isolation, security hardening for fork PR execution
- Cut CI time — right-size eval suites, deduplicate server startups, separate PR smoke tests from nightly full runs
- Improve developer experience — faster feedback, clearer failure messages, workflow orchestration
Requirements
- Nice to have: Large open-source project CI experience
- Nice to have: AMD ROCm CI pipelines
- Nice to have: Intel XPU CI pipelines
