Senior Software Engineer, CUTLASS Platform

Nvidia

Actively hiring Posted this week Verified listing
Santa Clara, CA · Austin, TX · Hillsboro, OR · Durham, NC · Redmond, WA Posted 3 days ago $152,000$241,500 / year

Market check

Salary context

Above market

How this pay compares to similar roles

Similar $176k
This role $197k
$102k most similar roles pay here $256k

This role pays more than 69% of similar roles. Most pay $142,400–$210,500 — the shaded band above. At the midpoint, this role pays about $197k versus about $176k 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 855 open roles on FindRole.

Listed pay typically runs $184,000–$287,500 across 843 roles with salary data.

Most-posted roles

View all roles at Nvidia

At a glance

TL;DR

Join NVIDIA’s CUTLASS team as a senior software engineer to drive the development of high-performance linear algebra and Tensor Core primitives for AI applications. You will design abstractions for GPU hardware features using MLIR, Python, and C++, develop core components like Tensor Core MMAs and schedulers in CUDA C++ and CUTLASS Python DSL, contribute to the MLIR-based backend compiler stack by designing dialects and passes, and author example kernels showcasing novel GPU hardware features. Ideal candidates have a Master’s or PhD in Computer Science with 3+ years of industry experience, strong proficiency in C++, expertise in high-performance code generation and compiler optimizations, hands-on experience with NVVM/PTX for GPUs, and knowledge of deep learning models and frameworks.

What you'll do

  • Develop core components of CUTLASS using CUDA C++ and Python DSL for Tensor Core MMAs and other GPU features.
  • Design MLIR dialects and compiler passes to enhance the backend compiler stack for CUTLASS Python DSL.
  • Write example kernels that demonstrate the use of new GPU hardware features for high performance.
  • Provide feedback on programming models and assess future GPU hardware feature performance with CUDA teams.
  • Create high-performance kernels at low levels like NVVM/PTX for GPUs or similar parallel processing architectures.

What we're looking for

  • Masters or PhD in Computer Science/Engineering or equivalent experience.
  • 3+ years of industry experience with high-performance code generation.
  • Strong C++ programming skills and software design expertise.
  • Experience writing high-performance kernels for GPUs at low levels.
  • Deep understanding of computer architecture and parallel computing models.
  • Hands-on compiler design experience, particularly in MLIR.

More like this

Similar roles

Software Engineer, Senior

Booz Allen Hamilton

Herndon, VA 69 days ago $86,800$198,000
Java Kubernetes Docker Spring Framework Spring Boot AWS Bitbucket Jenkins Linux REST CI/CD Ansible MongoDB Apache NiFi Kafka

Software Engineer, Senior

Booz Allen Hamilton

Springfield, VA 27 days ago $86,800$198,000
Java JavaScript Agile JMeter Jenkins Swagger Nexus Apigee GitHub GitLab AWS Bash Curl XML JSON SQL

Software Engineer, Senior

Booz Allen Hamilton

Nellis Afb, NV 21 days ago $86,900$198,000
DevSecOps CI/CD Kubernetes Docker Git AI ML Python Java JavaScript PostgreSQL AWS Azure Grafana Prometheus Agile Microservices APIs Terraform Maven SC2S MSS

Software Engineer, Senior

Booz Allen Hamilton

Fort Belvoir, VA 7 days ago $86,800$198,000
Python Java C++ Linux Agile JIRA Git Docker Jenkins CI/CD Roc Curve Confusion Matrix Geospatial Data Spatial Transformations Embedded Systems API Design

Software Engineer, Senior

Booz Allen Hamilton

MD 52 days ago $86,900$198,000
React Next.JS Git Jenkins GitLab CI/CD Express Flask Spring FastAPI Python Docker Kubernetes Elasticsearch Kibana Redis Kafka Nginx AWS HAProxy Grafana