The role involves leading the development and optimization of storage protocol stacks and device drivers within Linux and VMWare environments, focusing on high-performance, reliable data storage solutions, while mentoring engineering teams and contributing to the broader storage ecosystem.
Key Responsibilities
Own the development, maintenance, and optimization of Linux and VMWare initiator stacks for storage protocols such as NVMe over Fabrics and Fibre Channel
Drive system resilience by architecting enhancements for Fibre Channel and NIC driver stacks to improve reliability, availability, and serviceability
Mentor engineering team members through complex project deliveries, conduct code reviews, and set technical standards
Act as the final escalation point for challenging system-level bugs, providing root-cause analysis and long-term fixes
Optimize initiator behavior for maximum throughput and minimum latency, contributing performance improvements to the Linux upstream kernel
Requirements
Proven expertise in Linux Unix kernel development and writing robust device drivers, specifically within storage or networking subsystems.
Deep technical command of storage protocols such as NVMe TCP, ROCE, Fibre Channel (FC), or SCSI FCP, including experience designing and implementing significant components of these stacks.
Demonstrated ability to lead complex engineering projects from conception to delivery while mentoring peers and fostering a culture of high-quality, automated-first development.
Expert-level debugging skills for complex system kernel issues and a track record of using performance analysis tools to optimize storage system bottlenecks.
Experience owning the Protocol Lifecycle, including leading the development, maintenance, and optimization of Linux and VMWare initiator stacks NVMeoF, FC-SCSI, iSCSI, and target drivers to ensure seamless, high-performance integration with storage hardware.
Experience driving system resilience by architecting enhancements for Fibre Channel and NIC driver stacks that improve Reliability, Availability, and Serviceability (RAS), specifically focusing on multipathing logic and link health monitoring.
Ability to act as the final escalation point for the most challenging system-level bugs found in the field or internal testing, utilizing protocol analyzers and kernel debugging tools to provide root-cause analysis and long-term fixes.
Ability to optimize initiator behavior for maximum throughput and minimum latency, contributing key performance enhancements and bug fixes back to the Linux upstream kernel to benefit the broader storage community.
Willingness and ability to work primarily in an in-office environment at the OFFICE_LOCATION office in compliance with company policies, unless on PTO, work travel, or other approved leave.
Benefits & Perks
Flexible time off
Wellness resources
Company-sponsored team events
Ready to Apply?
Join Pure Storage and make an impact in renewable energy