Principal Engineer, CUDA UMD - GPU Kernel Scheduling

Nvidia

Confirmed live yesterday High trust

Quick summary

Work type: On-site
Location: Santa Clara, CA
Salary: $272,000–$431,250 / yr
Posted: 11 days ago
Freshness: Confirmed live yesterday
Closes: Nov 1, 2026
Nearby: 99+ roles within 25 mi

Market check

Salary context

Above market

How this pay compares to similar roles

Similar $219k

This role $352k

$136k most similar roles pay here $463k

This role pays more than 99% of similar roles. Most pay $188,562–$248,800 — the shaded band above. At the midpoint, this role pays about $352k versus about $219k 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 896 open roles on FindRole.

Listed pay typically runs $184,000–$287,500 across 876 roles with salary data.

Most-posted roles

View all roles at Nvidia

At a glance

TL;DR · Principal Engineer, CUDA UMD - GPU Kernel Scheduling

Role Posting Log in to save

Principal Engineer, CUDA UMD - GPU Kernel Scheduling joins the team responsible for developing the CUDA Driver, a core component for accelerating general purpose computation on the GPU. This role involves architecting and implementing new features, coordinating development efforts across multiple teams, and defining forward-looking improvements to CUDA APIs and programming models. The position focuses on extending functionality like CUDA Graphs to improve the scheduling of AI/ML workloads for better efficiency. Candidates must possess expert C and C++ skills, experience with large codebases, and a deep understanding of operating system interfaces including threads, process control, and virtual memory. Technical requirements include multithreaded programming, kernel mode development, and knowledge of system architecture like interconnects and memory hierarchy. The work addresses the technical challenge of optimizing hardware for diverse workloads such as deep learning, scientific computation, and video games.

What does a Engineer earn in California?

Median $208000 from 94 postings across 22 companies.

See salary data

Skills

C C++ CUDA Parallel Computing Kernel Mode Development Linux Systems Software Device Drivers Operating System Interfaces Virtual Memory Process Control

What you'll do

Architect and implement new features for the CUDA Driver to accelerate general purpose computation.
Coordinate and drive development efforts across multiple teams to deliver core platform improvements.
Define forward-looking improvements to CUDA APIs and programming models.
Extend CUDA programming models and functionality, specifically focusing on CUDA Graphs.
Optimize the scheduling of AI/ML workloads on GPUs for increased efficiency and speed.
Write maintainable, well-tested code across multiple operating systems.
Develop solutions to enhance hardware performance for deep learning, scientific computing, and autonomous vehicles.

What we're looking for

BS or MS degree in Computer Science, Electrical Engineering, or a related field (or equivalent experience).
Strong C and C++ programming skills.
Minimum of 15 years of related development experience.
Experience driving projects across multiple teams.
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 and presentation skills.

Save