Principal SSD Debug Engineer - 2282

Kioxia•Folsom, CA

About The Position

KIOXIA America, Inc. is seeking a technically driven Principal SSD Debug Engineer to lead complex failure investigations involving enterprise and data center SSDs used in hyperscale server environments. The role requires expertise across server hardware architecture, operating-system storage stacks, NVMe/PCIe protocols, and SSD firmware. The engineer will independently reproduce system-level failures, isolate root causes in host platforms and SSDs, analyze and modify embedded firmware, and guide cross-functional teams toward sustainable resolutions. The position covers troubleshooting throughout the storage subsystem, from applications and operating-system drivers through PCIe interfaces to SSD controller firmware and NAND media. It also involves performance investigations, hands-on laboratory work, customer-facing failure analysis, and technical documentation. The role collaborates with globally distributed engineering teams and may require domestic and international travel. No relocation assistance is provided.

Requirements

Bachelor’s degree in computer engineering or an equivalent field and at least 10 years of experience in a related technical field, or a master’s degree in computer engineering or an equivalent field and at least 8 years of experience in a related technical field.
Strong hands-on C programming and debugging experience in embedded firmware or low-level systems software.
Ability to read, understand, modify, and debug complex embedded firmware codebases.
Strong knowledge of firmware concurrency, including mutexes, semaphores, interrupts, atomic operations, race conditions, and deadlocks.
Experience debugging memory corruption, pointer errors, stack overflows, timing-sensitive failures, and hardware/software interactions.
Working knowledge of BMC functionality, IPMI/Redfish interfaces, server management logs, BIOS/UEFI, and platform initialization.
Proficiency with Linux storage debugging tools, including dmesg, journalctl, nvme-cli, fio, lspci, perf, and kernel crash analysis tools.
In-depth understanding of NVMe and PCIe specifications and demonstrated experience debugging protocol-level failures.
Ability to interpret specification requirements and validate firmware behavior against protocol standards.
Solid understanding of SSD architecture, including controller SoCs, NAND flash, FTL, garbage collection, wear leveling, and error handling.
Familiarity with SoC architecture, memory-mapped registers, register-level programming, and firmware debugging interfaces such as JTAG.
Strong analytical skills, including the ability to develop technical hypotheses, design targeted experiments, and validate root causes using measurable evidence.
Strong written and verbal technical communication skills and experience collaborating across globally distributed engineering teams.
SSD firmware architecture and/or validation/test experience.
Ability to travel domestically and internationally when needed.

Responsibilities

Troubleshoot failures across applications, file systems, block layers, operating-system storage drivers, hypervisors, PCIe subsystems, and SSDs to isolate host-, platform-, and SSD-level issues.
Investigate SSD interactions with server components, including CPUs, PCIe root complexes, chipsets, BMCs, BIOS, and system firmware.
Investigate storage failures involving multiple controller configurations, resource contention, concurrency, thermal behavior, power-loss protection (PLP), virtualization-related driver interactions, and platform-specific behavior.
Analyze Linux and Windows host logs, kernel crash dumps, PCIe protocol traces, BMC event logs, and system telemetry to identify failure mechanisms.
Lead cross-functional debugging with SSD firmware, platform, and customer teams; define reproducible test cases and drive corrective actions to closure.
Collaborate with globally distributed engineering teams to resolve technical issues across time zones.
Correlate host and SSD telemetry with firmware source code and hardware behavior, and drive root-cause analysis to closure.
Develop debug firmware in C across the SSD firmware stack to accelerate root-cause analysis.
Troubleshoot SSD performance issues, reduce tail latency, and improve IOPS and throughput.
Perform laboratory work to replicate reported issues.
Create 8D and failure-analysis reports and explain findings to customers.
Write product use-case technical white papers as needed.
Travel domestically and internationally when needed.