GPU Programming Software Engineer

Micro1 is seeking a highly skilled GPU Programming Software Engineer to join our team in a fully remote capacity. In this role, you will leverage your technical expertise to design and implement GPU-related tasks specifically focused on training Large Language Models, with a strong emphasis on performance optimization and system architecture.

Key responsibilities

• Design, implement, and optimize high-performance GPU-based software solutions using CUDA, WebGPU, or GLSL.
• Profile and fine-tune complex GPU kernels and shaders to ensure maximum efficiency and throughput.
• Develop robust host-side logic and seamless integrations using C++.
• Collaborate on architectural decisions to improve the scalability of GPU-accelerated workflows.

Requirements

• Advanced experience with GPU programming languages capable of running on NVIDIA hardware.
• Strong background in domains such as Graphics Programming, Machine Learning acceleration, Scientific Computing, or High-Performance Computing.
• High proficiency in C++ development.
• Ability to work independently and deliver high-quality code within a fast-paced, output-based environment.

What we offer

• The opportunity to work on cutting-edge projects involving LLM training and GPU acceleration.
• A fully remote work environment that allows for flexibility in your professional workflow.
• Engagement in a high-impact role where your technical contributions directly influence performance outcomes.
• A streamlined onboarding process designed to get you started on impactful tasks quickly.