Shakudo is building the world's first operating system for data and AI. We are seeking an Infrastructure Engineer to join our Business Automation team to own and operate the internal systems, infrastructure, and AI Gateway product that power Shakudo at scale.
This is a hands-on role for someone who thrives on keeping production systems reliable, secure, and fast. You will be responsible for everything from physical servers and DGX machines to CI/CD pipelines and customer-facing AI Gateway infrastructure. You will also contribute directly to product hardening, security, and DevOps practices across the platform.
Key Responsibilities
Maintain and operate internal services for the rest of the Shakudo employees, including proprietary applications for sales and ETL pipelinesMaintain and operate DGX machines that host LLMs for the team's useMaintain and operate Shakudo's product for Shakudo's internal use, and contribute to product hardening, security, and DevOps practicesMaintain and operate physical servers for Kubernetes clusters and ensure uptimeCreate CI/CD pipelines for internal deploymentsMaintain and operate the AI Gateway product for customers, ensure uptime, and contribute to product roadmap
Qualifications
8+ years of experience across software, data, platform, or AI engineering roles5+ years of strong experience with Kubernetes cluster operation and DevOpsProficiency in RustExperience operating production infrastructure at scale, including physical servers, GPU clusters, and CI/CD systemsStrong background in security hardening, observability, and reliability engineeringExperience with AI/ML infrastructure, including LLM hosting and inference serving