Staff Software Engineer - Infrastructure Storage

Role description

Role Overview

We are seeking a seasoned Staff Storage Software Engineer with deep experience designing and deploying storage protocol solutions at scale across object, block, and file paradigms. This is a unique opportunity to work at the intersection of large-scale distributed systems and the rapidly evolving field of artificial intelligence infrastructure.

What You Will Do

Design, develop, and maintain high-performance storage systems software with a focus on performance, scalability, reliability, and operational simplicity. Implement and optimize storage protocol APIs across file (NFS, SMB, Lustre), block (NVMe-oF, iSCSI, Fibre Channel), and object (S3) access patterns.

Why It Might Be a Fit

You will have a significant impact on the future of AI, building the foundational infrastructure that powers some of the most advanced AI research and products in the world. You will work closely with storage software and networking teams to execute cross-functional infrastructure initiatives and new data center deployments.

Requirements

• 10+ years of experience in storage systems engineering
• 5+ years in a technical lead or Staff+ IC role
• Proven track record designing and operating storage infrastructure at scale
• Experience leading technical projects end-to-end
• Background working in high-performance computing, AI/ML infrastructure, or large-scale cloud storage environments
• Strong proficiency in one or more low-level systems programming languages: C, C++, Rust, or Go
• Experience with kernel-level storage drivers, user-space I/O frameworks, or storage daemon development
• Familiarity with DPDK and SPDK and their role in building high-performance, kernel-bypass storage and networking data paths
• Deep hands-on experience with two or more storage protocols: object (S3 or similar), block (iSCSI, Fibre Channel, NVMe-oF), or file (NFS, SMB, Lustre, DAOS)
• Experience implementing or maintaining storage protocol servers or clients in production
• Familiarity with storage API performance characteristics such as latency, throughput, IOPS and the ability to diagnose and resolve bottlenecks at the protocol level
• Experience profiling and tuning storage systems for throughput, latency, and IOPS under real production workloads
• Familiarity with tools such as fio, blktrace, perf, eBPF/bpftrace, or equivalent for storage performance analysis
• Understanding of I/O scheduling, caching layers, write amplification, and related performance tradeoffs
• Familiarity with NVMe, NVMe-oF, and RDMA (RoCE or InfiniBand) and their impact on storage system architecture
• Working knowledge of DPUs (e.g., NVIDIA BlueField) and their role in offloading storage and networking data paths
• Experience with GPU-direct storage or similar zero-copy data paths
• Comfort working in a physical data center environment — understanding rack-scale infrastructure, storage array hardware, cabling, and failure domains
• Experience building and operating storage systems with strong reliability expectations: designing for failure, building runbooks, and driving incident response
• Familiarity with storage observability tooling — metrics pipelines (Prometheus, Grafana), log aggregation, and tracing in distributed storage environments

Benefits

• Generous cash & equity compensation
• Health, dental, and vision coverage for you and your dependents
• Wellness and commuter stipends for select roles
• 401k Plan with 2% company match (USA employees)
• Flexible paid time off plan