Senior Software Engineer - SOC Platforms

NVIDIA•Santa Clara, CA

1d•$184,000 - $356,500

About The Position

NVIDIA is looking for a Senior GPU Platforms Engineer to be part of an innovative and ambitious group. This is an outstanding opportunity to work on groundbreaking GPU & SOC systems and platform software, driving the next era of accelerated computing. The role involves being a System Software Generalist, taking ownership for platform software including kernel device driver development, firmware / BIOS interactions, health monitoring, and system-level features on new GPU / SOC platforms and products. It also requires being an Observability stack expert, designing and developing high-performance, distributed observability platforms handling high-volume data (metrics, logs, traces etc.), real-time monitoring, logging, and alerting across diverse products and environments. Additionally, the role involves being a Full stack software engineer, developing production applications, solutions, and features for NVIDIA SOC products. The engineer will partner with software, driver, and product / data center/Cloud units to launch new GPU platforms, resolve sophisticated system challenges, and improve performance, features, and stability across configurations. Active engagement in code reviews and contribution to substantial production codebases using solid C/C++ and data pipeline, business intelligence skills is expected. Understanding how AI workloads map onto NVIDIA architectures and how these features impact latency, throughput, and cost is crucial. The role also requires developing and sustaining in-depth knowledge of OS and system software, concentrating on Linux internals, device drivers, kernel/user boundaries, concurrency, and performance profiling, and applying expertise in Operating Systems and Computer architecture to manage CPU–GPU interactions, PCIe, memory hierarchy, interrupts, and firmware/bootloaders.

Requirements

BS/MS/PhD (or equivalent experience) in Computer Science or a related degree, along with multiple years of experience in systems, platform, embedded, or GPU software roles.
At least 10 years of experience in developing SOC systems and platform software.
Strong hands-on experience developing system software, covering Linux internals, device drivers, kernel/user boundaries, concurrency, and performance profiling.
Hands-on experience with building modern observability architectures, (including metrics, logs, and traces), distributed systems design and modern business intelligence and analytics stack.
Proficiency in high-performance, secure, production software stack, backend systems programming.
A solid understanding of Advance Operating Systems, Advance Database, Computer Architecture and Distributed systems.
Experience developing AI/ML applications, integrating with various features and applications.
Proven record of designing scalable, secure solutions for products.

Nice To Haves

Experience programming and debugging skills for SOC platforms with experience on various devices, across x86 & ARM system architecture.
In depth knowledge on Linux and / or Windows OS, Networking, virtualization.
Demonstrated proficiency in C/C++ along with strong coding abilities, having worked on extensive production codebases and conducted code reviews.

Responsibilities

Take ownership for platform software including kernel device driver development, firmware / BIOS interactions, health monitoring, system-level features on new GPU / SOC platforms and products.
Design and develop high-performance, distributed observability platforms handling high-volume data (metrics, logs, traces etc.), real time monitoring, logging and alerting across diverse products having diverse environments and develop backend pipeline, analytics platform with a focus on performance at scale.
Develop productions applications, solutions and features for NVIDIA SOC products.
Partnering with software, driver, and product / data center/Cloud units, launch new GPU platforms, resolve sophisticated system challenges, and improve performance, features and stability across configurations.
Engage actively in code reviews and contribute to substantial production codebases using solid C/C++ and data pipeline, business intelligence skills.
Understand how AI workloads map onto NVIDIA architectures (streaming multiprocessors, Tensor Cores, memory hierarchy, NVLink , PCIe, MIG, etc.), and how these architectural features impact latency, throughput, and cost.
Develop and sustain an in-depth knowledge of OS and system software, concentrating on Linux internals, device drivers, kernel/user boundaries, concurrency, and performance profiling.
Apply expertise in Operating Systems, Computer architecture to manage CPU–GPU interactions, PCIe, memory hierarchy, interrupts, and firmware/bootloaders.