Senior AI Infrastructure Engineer, Physical Infrastructure
Anduril IndustriesBase Salary
$166k - $220k/yr
Responsibilities
- Rack, stack, cable, bring up, and burn-in validate H200, B200, B300, and NVL72 GPU compute systems.
- Build and tune NVLink, InfiniBand, RoCE, and Spectrum-X interconnect fabrics for large GPU clusters.
- Integrate VAST, DDN, Weka, and other high-performance parallel storage for distributed training workloads.
- Automate cluster deployment, infrastructure-as-code configuration, firmware and driver management, and fabric setup.
- Operate and extend Kubernetes and Run:AI environments for GPU scheduling, quota management, and multi-tenant isolation.
- Own fleet health through monitoring, alerting, fault triage, observability, and automated hardware and network fault detection.
- Support engineers and researchers by debugging and optimizing workloads when infrastructure is the bottleneck.
- Partner with product-facing teams to translate emerging compute needs into platform capabilities.
Requirements
- 10+ years of hands-on infrastructure, HPC, or datacenter engineering experience supporting GPU compute at scale.
- Hands-on experience bringing up, cabling, and managing firmware and drivers for H200, B200, B300, or comparable GPU systems.
- Experience with NVLink, InfiniBand, RoCE, or Spectrum-X in clusters containing hundreds of GPUs.
- Experience with VAST, DDN, Weka, Lustre, or similar high-performance parallel storage.
- Kubernetes experience is required; Run:AI or similar GPU scheduling and orchestration experience is strongly preferred.
- Strong automation experience building repeatable, automated deployment pipelines.
- Ability to lift and move 50+ pounds and perform physical datacenter work.
- Eligibility to obtain and maintain an active U.S. Top Secret clearance.
- Preferred experience with NVIDIA NVL72 rack-scale systems and LLM token-serving or inference infrastructure.
- Preferred experience tuning RoCE or InfiniBand network fabrics, including congestion control, adaptive routing, and QoS.
- Preferred familiarity with DCGM, fabric telemetry, and automated GPU or network fault detection.
- Preferred experience supporting shared infrastructure platforms for multiple internal customer teams.
Benefits
- Top-tier full-time benefits available at little to no cost to employees.
- Highly competitive equity grants are included in the majority of full-time offers.
- The role includes physical datacenter work and requires eligibility for an active U.S. Top Secret clearance.
Tech Stack
Categories
About Anduril Industries
Anduril is not a traditional defense contractor. We are shaping the future of defense, transforming US & allied military capabilities with advanced technology. We emphasize speed and results and control our products from start to finish, including funding R&D to selling finished products off the shelf. Today, Anduril is in a rapid growth phase, deploying technology in diverse locations and developing path-making products that will change defense forever. We believe that everyone at Anduril can be a catalyst. Your perspective can change lives, and we want to help you make your mark. Our team includes thinkers and doers working interdependently. We bring the brightest minds and best-in-class talent together with veterans who have lived the problems of our warfighters. If you like building quickly and seeing your work deployed in the real world, we want you at Anduril. With offices in Orange County, Washington DC, Seattle, Boston, Atlanta, London, and Sydney, our reach is wide. Check out our careers page at https://www.anduril.com/careers or send us an email at careers@anduril.com.