Latest AI JobsBrowse Jobs
D

Senior GPU Performance / Kernel Engineer

designworkstalentBellevueEngineering
Apply on company site
Salary
Not listed
Job type
Full-time
Work mode
Remote
Experience
Senior
Posted
2 Oct 2026
Status
Open · checked 7d ago

About this role

This position suits systems and performance engineers who enjoy deep technical challenges involving GPU computing, kernel optimization, and distributed artificial intelligence workloads. Located in Bellevue, Washington as a hybrid role, the position involves optimizing the data plane and maximizing performance for large-scale GPU infrastructure.

Role Overview

Designworkstalent seeks Senior GPU Performance / Kernel Engineers for a hybrid position in downtown Bellevue, Washington. The role centers on extracting maximum performance from large-scale GPU infrastructure by analyzing workload behavior and optimizing performance-critical code paths. The organization is a well-funded, rapidly growing artificial intelligence infrastructure company building a cloud platform designed to support training, fine-tuning, inference, and agentic artificial intelligence applications.

Key Responsibilities

Profile, analyze, and optimize graphical processing unit kernels to improve latency, throughput, and overall utilization.
Identify and eliminate data-plane bottlenecks impacting graphical processing unit performance across large-scale artificial intelligence workloads.
Tune performance-critical workloads across training and inference environments.
Collaborate with artificial intelligence infrastructure, machine learning, and platform engineering teams to understand workload characteristics and optimize system behavior.
Develop benchmarking methodologies and performance measurement practices across graphical processing unit infrastructure.
Evaluate emerging graphical processing unit technologies, performance tools, and optimization techniques as hardware platforms evolve.
Contribute to engineering practices that improve graphical processing unit efficiency, scalability, and reliability across the fleet.

Requirements

Strong experience with graphical processing unit kernel development and performance optimization using technologies such as CUDA, ROCm, or comparable graphical processing unit programming frameworks.
Demonstrated experience improving graphical processing unit utilization, reducing latency, or increasing throughput for production artificial intelligence workloads.
Strong understanding of graphical processing unit architecture, memory hierarchy, parallel computing, and the data path from application layer to hardware execution.
Experience profiling and debugging performance issues in complex artificial intelligence or distributed computing environments.
Ability to independently own technically complex problems and drive solutions in a fast-moving engineering environment.
Strong systems programming and performance engineering mindset.

Nice to Have

Experience optimizing workloads across multiple graphical processing unit platforms, including NVIDIA and AMD architectures.
Experience with graphical processing unit compiler technologies, runtime optimization, or low-level systems performance.
Contributions to open-source graphical processing unit performance projects, compiler tooling, or artificial intelligence systems optimization.
Background working with large-scale artificial intelligence training, inference platforms, high-performance computing environments, or cloud graphical processing unit infrastructure.
Familiarity with graphical processing unit profiling and optimization tools such as Nsight Systems, Nsight Compute, ROCm profiling tools, or similar technologies.

Skills and Tools

CUDA
ROCm
NVIDIA architectures
AMD architectures
Nsight Systems
Nsight Compute
ROCm profiling tools

Salary and Benefits

Competitive base pay for the Bellevue market with eligibility for merit increases, annual bonus, and long-term incentives based on individual performance.
Medical, dental, and vision insurance for United States based employees.
A 401(k) plan with company match.
Paid holidays per calendar year.

About the Company

The organization is a well-funded, rapidly growing artificial intelligence infrastructure company backed by significant long-term investment. It combines the speed, ownership, and innovation of a startup with the stability and resources of an established parent organization, featuring lean, highly collaborative, and artificial intelligence-native engineering teams.

How to Apply

Apply on the official company careers page.

Skills and tech stack

Questions candidates ask

Where is this job located?

This is a hybrid role based in downtown Bellevue, Washington, requiring approximately three days per week in the office. Candidates elsewhere in the United States who are open to relocation may also apply.

Is visa sponsorship available?

No, United States work authorization is required and visa sponsorship is not currently available.

What kind of experience is required for this role?

The role requires strong experience with graphical processing unit kernel development and performance optimization using frameworks like CUDA or ROCm, demonstrated experience improving utilization and throughput for production workloads, a strong understanding of hardware architecture and memory hierarchy, and experience profiling performance issues.

What benefits are included?

United States based employees receive medical, dental, and vision insurance, a 401(k) plan with company match, paid holidays per calendar year, and eligibility for merit increases, annual bonuses, and long-term incentives.

What is the expected in-office schedule?

The position is a hybrid role requiring approximately three days per week in the Bellevue office.

Ready to apply?

The application is on the official designworkstalent careers page.

Apply on company site