GPU Programming Software Engineer
$60–$95/hr
RemoteRemote In this role, you will apply your expertise as a GPU programmer to design GPU related tasks to train LLMs, focusing on performance and architecture. Scope of Work Design, implement, and optimizContracttechnology
Apply NowKey details
- Role type
- Contract
- Compensation
- $60–$95/hr
- Work arrangement
- Remote
- Category
- technology
- Openings
- 25
About this role
Design high-performance GPU programming tasks that help train large language models, with a focus on performance optimization and GPU architecture.
Key Responsibilities- Design, implement, and optimize GPU-based software solutions using CUDA, WebGPU, or GLSL.
- Profile and refine GPU kernels and shaders to maximize performance and efficiency.
- Develop host-side logic and integrations in C++.
- Create GPU-focused tasks for LLM training, emphasizing performance and architecture.
- Advanced experience with a GPU programming language that runs on NVIDIA chips.
- Proficiency in C++.
- Experience with CUDA, WebGPU, or GLSL.
- Background in graphics programming, machine learning acceleration, scientific computing, high-performance computing, or another GPU-focused domain.
- Remote independent contractor engagement.
- Work is paid per completed task that meets project specifications, and the time needed may vary based on experience and workflow.
- Minimum task submission requirements apply, including a minimum number of tasks submitted each week.
- Roles are typically filled within 48 hours. Selected candidates should be ready to begin their first tasks within 24 to 48 hours after completing onboarding.
- $60 to $95 per hour.
- Apply online and complete the required account and onboarding steps. Successful applicants will be prepared to begin task work shortly after onboarding is complete.