Senior Software Architect, Deep Learning and HPC Communications

Nvidia

Confirmed live today High trust

Remote

Quick summary

Work type: Remote
Location: Santa Clara, CAWestford, MAAustin, TXDurham, NC
Salary: $184,000–$287,500 / yr
Employment: Full-time
Posted: 3 days ago
Freshness: Confirmed live today
Nearby: 99+ roles within 25 mi

Market check

Salary context

Above market

How this pay compares to similar roles

Similar $215k

This role $236k

$160k $301k

below market most similar roles pay here above market

This role pays more than 77% of similar roles. Most pay $194,825–$235,750 — the blue band above. At the midpoint, this role pays about $236k versus about $215k 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 Software Architect, Deep Learning and HPC Communications

Role Posting Log in to save

The Senior Software Architect - Deep Learning and HPC Communications joins the GPU Communications Libraries and Networking team to co-design next-generation data center platforms and scalable communications software. This role involves investigating performance bottlenecks, designing new communication technologies to accelerate AI and HPC workloads, and building proofs-of-concept through quantitative modeling and simulation for large GPU clusters. The successful candidate will utilize C/C++ programming skills, Linux, and parallel programming models like MPI and SHMEM. Required expertise includes communication runtimes such as NCCL, NVSHMEM, OpenSHMEM, UCX, or UCC, alongside a deep understanding of operating systems, computer architecture, and network topologies like InfiniBand and NVLink. The work focuses on optimizing high-speed interconnects to improve end-to-end application performance for massive compute demands.

Skills

C++ CUDA MPI NCCL NVSHMEM UCX PyTorch TensorFlow InfiniBand NVLink PCIe Linux HPC Deep Learning Parallel Programming Networking RoCE SHMEM OpenSHMEM

What you'll do

Identify performance bottlenecks in current systems to improve communication efficiency.
Design and implement new communication technologies to accelerate AI and HPC workloads.
Co-design next-generation platforms by exploring innovative hardware and software solutions.
Build proofs-of-concept and conduct experiments to evaluate new technical innovations.
Perform quantitative modeling to drive the development of new technologies.
Use simulations to explore the performance of large-scale GPU clusters.

What we're looking for

M.S./Ph.D. degree in CS/CE or equivalent experience.
5+ years of relevant experience.
Excellent C/C++ programming and debugging skills.
Experience with parallel programming models (MPI, SHMEM) and at least one communication runtime (MPI, NCCL, NVSHMEM, OpenSHMEM, UCX, UCC).
Deep understanding of operating systems, computer and system architecture.
Solid fundamentals of network architecture, topology, algorithms, and communication scaling relevant to AI and HPC workloads.
Strong experience with Linux.
Experience with CUDA programming and NVIDIA GPUs (preferred).

Save