Senior Software Engineer - CUDA and Unified Memory

NVIDIA

  • Santa Clara, CA ; Austin, TX
  • On-site
  • Senior level
  • 10+ yrs experience
  • Backend Engineering
  • Visa: not specified
  • $184k–$357k

The role in 30 seconds

We are hiring software engineers to work on the CUDA driver, a core component of NVIDIA's platform for accelerating general purpose computation on the GPU. Our team delivers features and improvements to better realize the potential of NVIDIA hardware for a growing range of computational workloads. CUDA defines a unified programming model across a range of system configurations and hardware capabilities.

Is this role a fit for you?

The backgrounds this role is most likely to hire from, as RoleStack reads the posting.

Strong match

  • B2B infrastructure / API / developer tools
  • Software, SaaS & AI Platform
  • Internal tooling / back-office systems
  • Enterprise-scale (high availability, compliance, large distributed systems)
  • Growth-stage (scaling existing systems, reliability concerns)

Workable stretch

  • B2C consumer-facing application
  • Creator / builder / self-serve tool
  • Marketplace / multi-sided platform
  • Startup / greenfield (build from scratch, speed over polish)

Harder transition

  • Embedded systems / hardware-adjacent
  • Data platform / ML pipeline
  • Regulated environment (healthcare, finance, government)

Industry: Semiconductors & Electronics. See your personal match score

What they're really screening for

Must-haves

  • PLUS BS or MS degree in Computer Science, Electrical Engineering or related field (or equivalent experience)
  • CORE Strong C programming skills
  • CORE Minimum of 10+ years of related development experience
  • PLUS Experience working with large codebases
  • CORE Background with operating system interfaces for threads, process control, and virtual memory
  • CORE Experience writing and debugging multithreaded programs
  • PLUS Good written communication

Nice-to-haves

  • CORE Understanding of system level architecture, such as interconnects, memory hierarchy, interrupts, and memory-mapped IO
  • CORE Knowledge of memory coherence and consistency models
  • CORE Experience with kernel mode development
  • CORE Experience with Windows, Linux, or macOS driver development
  • PLUS Some familiarity w C++

Résumé keywords for this role

Terms the posting stresses. Include the ones you can honestly back up.

Tools & technologies

  • CUDA
  • Unified Memory
  • GPU
  • C
  • Linux
  • C++
  • kernel mode
  • userspace code
  • system architecture
  • interconnects
  • memory hierarchy
  • interrupts
  • memory-mapped IO
  • memory coherence
  • consistency models

Concepts & phrases

  • Senior Software Engineer
  • CUDA and Unified Memory
  • CUDA driver
  • accelerating general purpose computation
  • computational workloads
  • unified programming model
  • GPU hardware
  • kernel mode drivers
  • operating system
  • Unified Memory kernel driver
  • kernel memory management
  • design, coding expertise
  • best compute platform
  • sophisticated solutions
  • future direction of CUDA

Words that count as the same thing: "CUDA" ≈ Compute Unified Device Architecture, GPU programming model · "Unified Memory" ≈ Unified Memory kernel driver, shared memory management, GPU memory management · "virtual memory" ≈ memory management, address translation

Check my résumé against these keywords

Hiring at NVIDIA

All NVIDIA hiring data

Open senior roles RoleStack tracks right now, posted in the last 30 days.

More open roles at NVIDIA

Full job description from NVIDIA

From NVIDIA's posting. View the original

We are hiring software engineers to work on the CUDA driver, a core component of our platform for accelerating general purpose computation on the GPU. Our team delivers features and improvements to better realize the potential of NVIDIA hardware for a growing range of computational workloads, ranging from deep learning, scientific computation, and self-driving cars to video games and virtual reality!

Show full description Show less

CUDA defines a unified programming model across a range of system configurations and hardware capabilities. To accomplish this, the CUDA driver interacts with GPU hardware, kernel mode drivers, and the operating system. Unified Memory kernel driver provides kernel memory management that enables these advanced features.

What you'll be doing:

As a member of our team, you will apply your design, coding expertise, and creativity, and to collaborate with peers across NVIDIA to deliver upon the best compute platform in the world. You will craft sophisticated solutions to exciting problems shaping the future direction of CUDA!

• Architect, and implement new features for new chips and new kernel features

• Coordinate with other teams to accomplish your work daily

• Help define forward-looking improvements to the CUDA APIs and programming model

• Write effective, maintainable, and well-tested kernel and userspace code

• Develop code for multiple Linux operating systems

What we need to see:

• BS or MS degree in Computer Science, Electrical Engineering or related field (or equivalent experience)

• Strong C programming skills

• Minimum of 10+ years of related development experience

• Experience working with large codebases

• Background with operating system interfaces for threads, process control, and virtual memory

• Experience writing and debugging multithreaded programs

• Good written communication

Ways to stand out from the crowd:

• Understanding of system level architecture, such as interconnects, memory hierarchy, interrupts, and memory-mapped IO

• Knowledge of memory coherence and consistency models

• Experience with kernel mode development

• Experience with Windows, Linux, or macOS driver development

• Some familiarity w C++​

Your base salary will be determined based on your location, experience, and other objective job-related factors. The expected base salary ranges for this position are:
184,000 USD – 287,500 USD for Level 4; and 224,000 USD – 356,500 USD for Level 5.

You will also be eligible for equity and benefits.

Applications for this job will be accepted at least until November 9, 2026.

This posting is for an existing vacancy.

NVIDIA uses AI tools in its recruiting processes.

NVIDIA is committed to fostering an inclusive work environment and proud to be an equal opportunity employer. As we highly value diversity in our current and future employees, we do not discriminate (including in our hiring and promotion practices) on the basis of race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law.

FAQ

How much does a Senior Software Engineer - CUDA and Unified Memory at NVIDIA make?

The posted pay for this role is $184k–$357k a year.

How much experience do you need?

The posting asks for 10+ years in related development. It is a senior-level role.

Does NVIDIA sponsor visas for this role?

The posting does not say whether visa sponsorship is available. Ask the recruiter before you apply.

Is this role remote?

It is an on-site role.

What tools and technologies does the posting mention?

CUDA, Unified Memory, GPU, C, Linux, C++, kernel mode, userspace code, system architecture, interconnects, memory hierarchy, interrupts, memory-mapped IO, memory coherence, consistency models.