Senior Infrastructure Engineer
DeepInfraVisit DeepInfra website
AI inference cloud offering OpenAI-compatible APIs for machine-learning models, private deployments, and GPU infrastructure.
Palo Alto, United States
Funding history
About DeepInfra
DeepInfra provides hosted AI inference for language, vision, embedding, image, video, and speech models, alongside private model deployments and dedicated GPU clusters.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will design, build, and operate high-performance data center networks across colocation sites. You will lead site deployments from planning through production, manage vendors and logistics, automate infrastructure operations, and travel to data centers to install and troubleshoot hardware.
Requirements
- 10+ years building and operating infrastructure for 24/7 production environments
- Hands-on experience with data center infrastructure and networking
- Experience with spine/leaf or Clos architectures, BGP, and network security
- Experience bringing colocation or data center infrastructure online
- Strong Linux troubleshooting skills across networking, compute, storage, and physical infrastructure
- Scripting and automation skills using Python, Bash, Ansible, or similar tools
- Ability to manage complex infrastructure projects across vendors, dependencies, and locations
- Experience working directly with data center, network, or hardware vendors
Responsibilities
- Design, build, and operate high-performance data center networks across colocation sites
- Own end-to-end site bring-ups, including designs, capacity planning, layouts, installation, turn-up, and production handoff
- Operate and improve compute-platform infrastructure using Linux, monitoring, and automation
- Manage infrastructure projects across vendors and sites, including timelines, dependencies, logistics, and risks
- Travel to data centers to install, connect, and troubleshoot hardware
- Serve as the primary technical contact for data center vendors and managed-infrastructure customers
- Build repeatable playbooks, standards, and automation for new-site deployments
- Source, evaluate, and secure data center and colocation space
- Lead commercial negotiations with data center, network, and hardware vendors
