Senior System Software Engineer, GPU Performance

Nvidia

Confirmed live today High trust

Remote

Quick summary

Work type: Remote
Location: Santa Clara, CA
Salary: $152,000–$241,500 / yr
Employment: Full-time
Posted: 3 days ago
Freshness: Confirmed live today
Nearby: 99+ roles within 25 mi

Market check

Salary context

Competitive pay

How this pay compares to similar roles

Similar $213k

This role $197k

$139k $272k

below market most similar roles pay here above market

This role pays less than 56% of similar roles. Most pay $189,700–$235,750 — the blue band above. At the midpoint, this role pays about $197k versus about $213k for comparable roles.

Based on 240 similar postings.

Employer

About Nvidia

Nvidia is a leading designer of graphics processing units (GPUs) and system-on-chip units, powering gaming, professional visualization, data centers, and artificial intelligence workloads. Industry: Semiconductors & AI Computing

Nvidia currently has 1623 open roles on FindRole.

Listed pay typically runs $184,000–$287,500 across 1110 roles with salary data.

Most-posted roles

View all roles at Nvidia

At a glance

TL;DR · Senior System Software Engineer, GPU Performance

Role Posting Log in to save

The Senior System Software Engineer - GPU Performance joins the GPU Communications Libraries and Networking team to influence the roadmap for libraries like NCCL, NVSHMEM, and UCX. This role involves conducting in-depth performance characterization and analysis on large multi-GPU and multi-node clusters to optimize communication performance for Deep Learning and HPC applications. Key responsibilities include studying hardware and software interactions, evaluating proof-of-concepts, triaging customer performance issues, and building tools to visualize performance data. Candidates must possess experience with parallel programming, communication runtimes like MPI, and systems software fundamentals. Technical requirements include proficiency in C/C++, Python, and container tools like Kubernetes, SLURM, and Docker. The work addresses the challenge of maintaining high-speed interconnect performance across tens of thousands of GPUs using NVLink, PCIe, Infiniband, and Ethernet.

What does a System Software Engineer earn in California?

Median $235750 from 70 postings across 4 companies.

See salary data

Skills

HPC Parallel Programming C++ Python NCCL UCX NVSHMEM MPI CUDA PyTorch TensorFlow Kubernetes Docker Ansible SLURM Infiniband RDMA Ethernet PCIe NVLink

What you'll do

Conduct in-depth performance characterization and analysis on large multi-GPU and multi-node clusters.
Study the interaction of communication libraries with GPU, CPU, and networking hardware and software components.
Evaluate proof-of-concepts and conduct trade-off analyses for multiple technical solutions.
Triage and root-cause performance issues reported by customers.
Build tools and infrastructure to collect, visualize, and analyze performance data.
Implement micro-benchmarks in C/C++ and modify the existing codebase as required.
Debug performance issues across the entire hardware and software stack.

What we're looking for

M.S. (or equivalent experience) or PhD in Computer Science, or a related field with relevant performance engineering and HPC experience.
3+ years of experience with parallel programming and at least one communication runtime such as MPI, NCCL, UCX, or NVSHMEM.
Experience conducting performance benchmarking and triage on large scale HPC clusters.
Good understanding of computer system architecture, HW-SW interactions, and operating systems principles.
Ability to implement micro-benchmarks in C/C++ and read or modify the code base.
Ability to debug performance issues across the entire HW/SW stack.
Proficiency in a scripting language, preferably Python (preferred).
Familiarity with containers, cloud provisioning, and scheduling tools like Kubernetes, SLURM, Ansible, and Docker (preferred).

Save