Senior Storage Engineer

Runware

1d • Remote

About The Position

Runware is building an AI inference platform and an AI Factory that operates its own infrastructure. As Senior Storage Engineer, you will own the storage architecture for Runware’s AI supercomputer, connecting model weights, caches, and customer data in object storage across the US and Europe to NVMe and GPU memory across the fleet. You will design the data path, build its first version, validate systems on real hardware, and establish how storage is operated across every pod.

This is a hands-on senior individual-contributor role. You will work with inference, platform, and hardware teams, storage and NVMe vendors, and site teams deploying pods. The goal is to load cold models onto GPUs across the fleet in seconds, warm new pods before they receive traffic, and make storage failures invisible to developers. The role also owns storage reliability, capacity planning, security operations, and data residency, while using AI-based agents and automation to help a small team operate a large fleet.

Runware is remote-first, with in-person company gatherings twice a year. Core collaboration hours are observed, with flexibility outside them. Release cycles are fast and intense, followed by downtime. Travel to US and European sites is required as needed.

Requirements

• 8+ years in storage or systems engineering, including several years designing and operating storage at a company that operates its own hardware at scale.
• Demonstrated experience building storage systems, taking a design from concept to petabytes in production.
• Deep, current, hands-on Linux storage expertise, including the block layer, io_uring and NVMe queues, XFS, ext4 and ZFS file systems, page cache, and I/O diagnostic tools.
• Production experience with at least one parallel or distributed file system, such as Lustre, WEKA, VAST, GPFS, or Ceph, and S3-compatible object storage at petabyte scale.
• Strong understanding of NVMe, NVMe-oF, RDMA transports, and storage networking, including diagnosing PCIe, drive, or switch bottlenecks.
• Fluency in a systems language such as Go, Rust, or C/C++, and Python; able to write tooling, benchmarks, and automation hands-on.
• Daily use of AI to accelerate scripting, benchmarking, analysis, documentation, and debugging, with a clear understanding of how these tools can change how a small team operates.
• Comfort owning outcomes in a fast-moving, ambiguous environment, making decisions with incomplete information, and being accountable for latency, durability, and cost.
• Able to travel to sites in the US and Europe as needed.

Nice To Haves

• Experience feeding large GPU fleets for AI training or inference, including GPUDirect Storage, NCCL-aware data loading, model weight caching, and loaders in vLLM, SGLang, TensorRT-LLM, or similar engines.
• Hands-on experience with InfiniBand or RoCE fabrics and 400G+ Ethernet from the storage side.
• Experience with content-addressed or deduplicated storage, erasure coding, and multi-region replication and consistency trade-offs.
• Kernel or driver contributions, or deep familiarity with SPDK, DPDK, or user-space storage stacks.
• Experience with Kubernetes CSI, Ceph or Rook on bare metal, and automation such as Ansible and Terraform with Prometheus and Grafana observability.
• Familiarity with storage hardware supply chains, including drive qualification, firmware lifecycle, enclosure and backplane design, spares, and RMA economics.
• Experience building or operating storage to meet data residency, sovereignty, or compliance requirements across jurisdictions.

Responsibilities

• Own end-to-end storage architecture for the fleet, including durable object storage, per-pod high-throughput storage, node-local NVMe cache, and cross-region replication and placement.
• Design and build the model distribution path, including decisions about transferring, chunking, deduplicating, prefetching, and pinning weights, and warming new pods before they receive production traffic.
• Profile and reduce model-load latency across the path from disk to GPU memory, including kernel, file system, NVMe-oF or RDMA transport, GPUDirect Storage, and inference-engine loader components.
• Select, benchmark, and operate parallel and distributed file systems, object storage, NVMe drives and enclosures, and storage-management software; validate choices on company hardware before deployment.
• Set and meet storage reliability and durability targets; own capacity planning, monitoring, alerting, drive health and failure prediction, rebuild behavior, backup and recovery, and storage-layer on-call.
• Create a documented and automated pod bring-up playbook so the storage tier can be provisioned, validated, and warmed within hours.
• Partner with inference engine, platform, and hardware engineering to ensure storage is operable at scale and apply production learnings to future servers and pods.
• Use LLM-based agents to automate benchmarks, runbooks, triage, and tooling.
• Own data residency and operational storage security, including encryption at rest, access control, retention, and in-country placement for sovereign deployments.
• Travel to US and European sites as needed.

Benefits

• Meaningful stock options.
• Remote-first work arrangement with core collaboration hours and flexibility outside those hours.
• Real downtime following fast and intense release cycles.
• Generous paid time off, including vacation, sick days, and public holidays.
• Paid maternity, paternity, and caregiver leave.
• Twice-yearly company retreats in inspiring locations.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed