Senior Software Engineer, CUTLASS Performance

Nvidia

Confirmed live today High trust

Quick summary

Work type: On-site
Location: Santa Clara, CAAustin, TXHillsboro, ORDurham, NCRedmond, WA
Salary: $152,000–$241,500 / yr
Employment: Full-time
Posted: 148 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 $178k

This role $197k

$109k $256k

below market most similar roles pay here above market

This role pays more than 70% of similar roles. Most pay $149,500–$206,450 — the blue band above. At the midpoint, this role pays about $197k versus about $178k 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 Engineer, CUTLASS Performance

Role Posting Log in to save

The Senior Software Engineer, CUTLASS Performance joins the Deep Learning Library team to optimize the CUTLASS open-source ecosystem for high-performance linear algebra and Tensor Core primitives. You will benchmark state-of-the-art deep learning model inference and training passes to identify GPU kernel and fusion opportunities. Your daily work involves identifying gaps between theoretical and realized performance, suggesting software improvements, and developing automated tooling for benchmarking and performance optimization loops. You will serve as the authoritative resource on kernel performance, collaborating with GPU architecture, DL frameworks, and QA teams. The role requires proficiency in C++ and Python, along with experience in software performance analysis, computer architecture, and parallel processing. You will solve technical bottlenecks in matrix multiply computations and deep learning networks to maximize GPU performance.

What does a Software Engineer earn in California?

Median $214500 from 1193 postings across 76 companies.

See salary data

Skills

C++ Python GPU PyTorch JAX SGLang vLLM TRT-LLM Deep Learning Performance Benchmarking Computer Architecture Parallel Processing Software Performance Analysis CUTLASS Tensor Core GEMM

What you'll do

Benchmark performance of state-of-the-art deep learning models to identify GPU kernel and fusion opportunities.
Identify performance gaps between theoretical and realized results to suggest software or model improvements.
Develop tools to automate benchmarking, analysis, and performance optimization loops for CUTLASS kernels.
Serve as the authoritative resource on kernel performance for the CUTLASS team.
Represent the CUTLASS team to GPU architecture, DL frameworks, and QA teams regarding performance.
Optimize high-performance linear algebra and Tensor Core primitives for NVIDIA GPUs.

What we're looking for

Masters or PhD degree in Computer Science, Computer Engineering, or related field (or equivalent experience).
3+ years of relevant industry experience.
Strong programming skills in Python and C++.
Experience in software performance analysis and optimization.
Deep understanding of computer architecture and familiarity with GPUs or similar parallel processing architectures.
Deep understanding of state-of-the-art DL model architectures (preferred).
Hands-on experience with performance benchmarking of DL frameworks like PyTorch, JAX, SGLang, vLLM, TRT-LLM, or others (preferred).
Experience in developing performance models and performance regression systems (preferred).