CUDA Engineering Expert | Remote - Contract

Xperteez Technology Pvt Ltd; United States; Remote; USD 138,000 - 248,000; Full time

Job summary

Xperteez Technology Pvt Ltd is seeking a CUDA Engineering Expert for a remote contractor role. You will analyze GPU kernels, profile performance with CUDA tools, and optimize throughput on modern hardware for an AI-focused project.

The work involves collaborating with an AI lab, refining C++/CUDA code, and delivering high-quality, real-world input into training pipelines. Responsibilities include refactoring code for portability across architectures, implementing GLSL and WebGPU shader logic,

Qualifications

• CUDA and C++ expertise with GPU kernel optimization.
• Experience with GLSL and WebGPU is a plus.
• Familiarity with GPU profilers and performance tuning.
• Strong communication and ability to document results.

Responsibilities

• Analyze, profile, and optimize GPU kernels using CUDA to maximize throughput.
• Refactor C++ and CUDA codebases for maintainability across GPUs.
• Implement shader logic using GLSL and WebGPU and integrate with pipelines.
• Document findings and performance improvements with clear reports.
• Collaborate with remote team and stay updated on GPU programming advances.

Skills

CUDA

C++

GLSL

WebGPU

Job description

Role Title: CUDA Engineering Expert

Role Type: Contractor

Location: Remote

We are 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'll apply your expertise to help train next-generation AI systems. Your work will shape how models learn, reason, and perform through high-quality, real-world input. No prior experience in AI is required — your domain knowledge is what matters.

Scope of Work

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.

Required Skills

• CUDA
• C++
• GLSL
• WebGPU

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 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.

Originally posted on Himalayas