CUDA Engineering Expert (Remote)

$60 – $100 / hour | Remote | Contract | 50 Openings)

--------------------------------

Overview:

SourceBridge Co. is engaging CUDA Engineering Experts to contribute to a cutting-edge customer project focused on GPU kernel optimization in collaboration with a leading AI lab. In this role, you will apply your low-level high-performance computing expertise to help train next-generation AI systems. Your work will directly shape how machine learning models learn, reason, and perform through high-quality, real-world input. No prior experience in AI is required—your GPU programming and kernel optimization domain knowledge are what matter most.

 

Responsibilities:

• Analyze, profile, and optimize GPU kernels using CUDA and relevant profiling tools to maximize computational throughput on modern hardware.
• Collaborate with project stakeholders to assess and identify kernel bottlenecks, proposing targeted optimization strategies.
• Refactor C++ and CUDA codebases for improved maintainability, efficiency, and adaptability across diverse GPU architectures.
• Implement shader logic and graphics workflows using GLSL and WebGPU, ensuring seamless integration with existing pipelines.
• Document key findings, optimization steps, and performance improvements with clear, actionable reports and technical communication.
• Contribute expertise to design discussions, supporting the evaluation of new GPU-based approaches and performance metrics.
• Stay informed on advancements in GPU programming and share relevant insights to enhance project outcomes.

 

Requirements:

• Core expertise in CUDA, C++, GLSL, and WebGPU.
• Strong command of GPU architecture, thread hierarchy, memory bandwidth optimization, and compute shader execution.
• Excellent technical writing skills to produce detailed profiling reports and technical documentation.
• Proven ability to analyze complex low-level codebases and resolve hardware execution bottlenecks in remote environments.

 

Preferred Qualifications:

• Demonstrated expertise in CUDA programming, with a strong track record of performance-tuning GPU kernels.
• Advanced C++ development skills, particularly in high-performance computing environments.
• Hands-on experience with GLSL and WebGPU for graphics and compute shader development.
• Proficiency using GPU profilers (such as NVIDIA Nsight, Visual Profiler, or similar tools) for guided optimization.
• Strong analytical abilities to evaluate and reason about kernel performance across hardware generations.
• Excellent written and verbal communication skills—clear documentation and technical reporting are essential.
• Experience collaborating in remote, cross-disciplinary project settings is a plus.

 

Benefits:

• Top-tier competitive hourly compensation ($60–$100/hr).
• 100% remote working flexibility.
• High-impact opportunity to work on GPU kernel optimization alongside top AI research labs.

 

Hiring Process:

1. Application Review: Evaluation of C++/CUDA codebase portfolio, GPU profiling experience, and low-level engineering track record.
2. Technical Assessment: Practical evaluation of CUDA kernel optimization, bottleneck identification using profiling tools, and WebGPU/GLSL shader review.
3. Onboarding: Remote project setup and integration with research engineering leads.

 

Why Join Us?

 

Partnering with SourceBridge Co. offers you an exceptional opportunity to apply your high-performance compute expertise to the frontier of artificial intelligence. You will collaborate with leading researchers to optimize GPU execution pipelines, solve critical hardware bottlenecks, and ensure next-generation models achieve maximum computational throughput.

 

Apply Now: