You will operate as a deep technical leader, influencing architecture and solving complex system-level challenges across distributed filesystems and performance engineering.
As a member of Technical Staff, you will be responsible for designing and building next-generation distributed storage systems for AI and HPC workloads, focusing on extreme performance and scalability. You will work with product architects and global engineering teams on advanced filesystems, data services, and performance-critical platform innovations.
You will:
Architect extreme-scale distributed storage systems tailored for AI model training and large-scale GPU clusters.
Design and develop high-performance, multi-threaded components in C/C++ on Linux/Unix platforms.
Lead the evolution of parallel filesystems (Lustre, GPFS) and scale-out NAS architectures.
Drive end-to-end performance analysis and optimization, identifying and eliminating bottlenecks in I/O paths and memory usage.
Partner with product architects and senior leadership to translate complex customer requirements into scalable, resilient technical solutions.
Essential Requirements:
Proven experience in designing distributed storage systems, filesystems, or high-performance computing (HPC) platforms.
Deep expertise in Linux/Unix operating systems, specifically in memory management, concurrency, and kernel-level I/O stacks.
Advanced proficiency in C/C++ development for multi-threaded, low-latency system environments.
Hands-on experience with high-performance protocols such as RDMA (InfiniBand/RoCE) and NVMe-over-Fabrics (NVMe-oF).
Strong technical leadership skills with experience guiding architectural decisions and mentoring engineers in globally distributed teams.
Desirable Requirements:
Expertise in parallel filesystems (e.g., Lustre, GPFS, CephFS) and optimizing data ingestion pipelines for large-scale AI/GPU workloads.
Experience with modern cloud-native storage, including Kubernetes/CSI, and a history of contributions to technical IP, patents, or industry standards.
