Member of Technical Staff, Supercomputing Infrastructure
San Francisco$200k - $400kFull-timePosted 2mo ago
About the role
Hands-on supercomputing infrastructure engineer responsible for owning and operating Inferact's high-performance compute infrastructure across heterogeneous hardware (NVIDIA GPUs, AMD GPUs, Google TPUs) and multiple providers to keep engineering productive, healthy, observable, and available around the clock.
Responsibilities
- Own cluster health, accelerator availability, monitoring, alerting, scheduling, access, diagnostics, and incident response across GPU and TPU environments.
- Work with engineering leadership to standardize provisioning, operation, debugging, and scaling of compute across providers and hardware platforms.
- Ensure infrastructure is healthy, available, observable, and usable around the clock.
- Impact how fast Inferact can build, test, and improve systems powering vLLM.
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 (networking, processes, storage, package management, shell scripting, logs, access control, debugging).
- Experience operating GPU servers (driver management, GPU health monitoring, node failures, memory errors, scheduler issues, hardware diagnostics).
- Experience with cluster scheduling/resource allocation using SLURM, Kubernetes, or equivalent tooling.
- Ability to own urgent infrastructure incidents end-to-end when compute issues block engineering teams.
- Ability to automate operational workflows using Bash, Python, Ansible, Terraform, Helm, or similar tooling.
Skills
Required:Cluster administrationLinux systems administrationGPU server operationCluster schedulingAutomation
Benefits
- generous health, dental, and vision benefits
- 401(k) company match
Last updated Oct 18, 2026. Interested? Apply on the company site.
About Inferact
Inferact is a startup founded by creators and core maintainers of vLLM, the most popular open-source LLM inference engine.
AIbessemer-ai-infrastructure-2026frontier hardwareinferenceinference engineinference-inflection-pointopen sourcevLLM
More open roles at Inferact
- Engineering Manager1w agoSan Francisco · Research & Engineering
- Enterprise Partnerships Manager2w agoSan Francisco · GTM
- GTM Engineer2w agoSan Francisco · GTM
- Strategic Finance Lead2w agoSan Francisco · Finance
- Member of Technical Staff, Vulnerability Management2w agoSan Francisco · Research & Engineering