CUDA Engineering Expert - Remote

YO AI Labs · via Himalayas ·

Budget / Salary$10–50
TypeContract
LocationUnited States
Posted2 hours ago
Job Description: CUDA Engineering Expert
Role Type: Contractor
Location: Remote
About the Role
We are seeking experienced CUDA Engineering Experts to contribute to a GPU optimization project in collaboration with a leading AI lab. You will apply your expertise in GPU programming, kernel optimization, and high-performance computing to evaluate and improve AI systems. No prior AI experience is required.
Scope of Work

Analyze, profile, and optimize GPU kernels using CUDA and relevant profiling tools.

Identify performance bottlenecks and develop targeted optimization strategies.

Refactor C++ and CUDA codebases to improve efficiency, maintainability, and compatibility across GPU architectures.

Implement graphics and compute shader logic using GLSL and WebGPU.

Document optimization methods, performance improvements, and technical findings.

Contribute to technical discussions and evaluate GPU-based approaches and performance metrics.

Stay updated on GPU programming advancements and share relevant technical insights.

Required Qualifications

Strong expertise in CUDA programming and GPU kernel optimization.

Advanced C++ development skills, particularly in high-performance computing.

Hands-on experience with GLSL and WebGPU for graphics and compute shader development.

Proficiency with GPU profiling tools such as NVIDIA Nsight, Visual Profiler, or equivalent.

Strong analytical and problem-solving skills, with the ability to evaluate kernel performance across GPU architectures.

Excellent written and verbal communication skills, including technical documentation and reporting.

Preferred Qualifications

Experience optimizing GPU workloads across different hardware generations.

Familiarity with modern GPU architectures and performance optimization techniques.

Experience collaborating with remote, cross-functional engineering teams.

Originally posted on Himalayas
cuda-engineer gpu-engineer gpu-performance-engineer c++-engineer hpc-engineer
Apply on Himalayas →

Job sourced from Himalayas. Applications happen directly on the original platform — we never collect your data.