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 hands-on supercomputing infrastructure engineer to own and operate the high-performance compute infrastructure that keeps Inferact engineering productive. Inferact runs on expensive, high-performance GPU and HPC clusters across neo-cloud and dedicated compute providers, on heterogeneous hardware that spans NVIDIA GPUs, AMD GPUs, and Google TPUs. Your job is to make sure that infrastructure is healthy, available, observable, and usable around the clock.

You'll take ownership of cluster health, accelerator availability, monitoring, alerting, scheduling, access, diagnostics, and incident response across the systems our engineers rely on every day, from NVIDIA and AMD GPU clusters to TPU environments. You'll work closely with engineering leadership and infrastructure owners to standardize how we provision, operate, debug, and scale compute across providers and hardware platforms. Your work will directly impact how fast Inferact can build, test, and improve the systems powering vLLM.

Skills and Qualifications

Minimum qualifications:

• Bachelor's degree or equivalent experience in computer science, engineering, systems administration, or similar.
• Hands-on experience administering large compute clusters, HPC environments, university or research clusters, supercomputing systems, or production GPU clusters.
• Strong Linux systems administration fundamentals across networking, processes, storage, package management, shell scripting, logs, access control, and system debugging.
• Experience operating GPU servers, including driver management, GPU health monitoring, node failures, memory errors, scheduler issues, and hardware diagnostics.
• Experience with cluster scheduling and resource allocation using SLURM, Kubernetes, or equivalent tooling.
• Ability to own urgent infrastructure incidents end-to-end when compute issues are blocking engineering teams.
• Ability to automate operational workflows using Bash, Python, Ansible, Terraform, Helm, or similar tooling.

Preferred qualifications:

• Experience managing 1,000+ GPGPUs in production.
• Experience operating GPU compute across providers such as Lambda, CoreWeave, Crusoe, Nebius, Together, Fireworks, RunPod, or similar environments.